Name: JobMojito
Author: jobmojito

JobMojito MCP

Run AI interviews, simulated personas and coaching sessions on JobMojito.

Tool-list grade A Remote · Streamable HTTP No auth needed 38 tools v1.3.2

No reviews yet by jobmojitoGitHub The publisher’s own endpoint — this marketplace is not in the path

93/100

tool-list score

tools declared

remote

at its publisher

—

calls last 7d

What it does

Run AI interviews, simulated personas and coaching sessions on JobMojito.

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user --transport http jobmojito-mcp https://mcp.jobmojito.com/mcp

# 2 — ask your agent for something these tools do
#   search_documentation, get_documentation, list_my_merchants and 35 more

JobMojito costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publishernot claimed

jobmojito1 server

1 category

All 1 server

Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

Search ALL JobMojito documentation. This is the single entry point. One call searches both documentation sources in parallel and returns a merged, source-labeled list — you do not need to choose a source or call a separate tool: • "developer" — developer.jobmojito.com: API reference, request/response schemas, tables, webhooks, code examples, integration guides. • "help" — help.jobmojito.c

Parameter	Type	Required	Notes
query	string	yes	Natural-language search query or keywords.
source	string	no	"all" (default), "developer", or "help" to restrict the search.
limit	integer	no	Max results per source (1-25).
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

Fetch the full content of a single JobMojito documentation page. Accepts a URL returned by search_documentation. For developer docs the clean Markdown (.md) variant is fetched automatically. Only developer.jobmojito.com and help.jobmojito.com URLs are allowed.

Parameter	Type	Required	Notes
url	string	yes	The documentation page URL.
max_chars	integer	no	Truncate content to this many characters (default 20000).
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

FALLBACK merchant list for clients WITHOUT UI support. Do NOT use this to choose or switch merchants when a UI is available — call jobmojito_configuration instead (it renders an interactive picker), and do not hand-format a merchant list as text. Use this tool only when the client cannot render MCP App UI. Returns the user's own account plus any sub-merchants; after a pick, pass `merchant_id=<c

Parameter	Type	Required	Notes
search	string	no	Optional case-insensitive filter on sub-merchant name.
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Interviews] Create a new interview and auto-generate its question sequence from position data. The interview_template_id you pass also sets the modality (voice-only vs realtime/pre-recorded avatar) — see list_avatars. Creates a new interview / coaching / assessment definition, generates its description, questions and candidate expectations via AI, and provisions default steps. Optionally pro

Parameter	Type	Required	Notes
name	string/null	yes	Interview / position name.
location	string/null	yes	Job location — a city/country, or remote. Required and must not be empty: when the job description gives no location, pass Not specified.
interview_template_id	string/null	yes	Id of the interview template to base this interview on.
mojito_language_code	string/null	yes	Platform language code used for the interview. Must be one of the platform-languages.json codes.
status	string/null	yes	Lifecycle status of the interview. Options — draft: Created but not published — not visible to candidates and cannot be run yet. Use to stage an interview before going live. \| active: Published an
type	string/null	yes	Product type of the interview. Options — interview: Standard candidate interview for a role — answers are AI-scored and produce a hiring recommendation. \| coaching: Practice/coaching session — can
visibility	string/null	yes	Who can discover and access the interview. Options — merchant_public: Listed on the merchant's public interview list — anyone with the merchant link can find and start it. \| merchant_invite: Invit
recording	string/null	no	Cheating/proctoring detection mode for candidate answers — this is NOT a full session recording. Video options also record the candidate. Omit/null to disable. Options — audio_first_5_answers: Audio
recording_full_session	string/null	no	Full interview-session recording (includes the avatar and voice) produced as a single file. Independent of recording. Omit/null to disable. Options — audio_all: Record the whole session audio (ava
environment	string/null	no	Which of your webhook environments results from this interview are delivered to. Defaults to production. Options — production: Live hiring. Results reach the webhooks configured as production. This
interview_type	string/null	no	Interview style — configures the AI avatar and shapes both the AI-generated questions and the follow-up questions asked during the interview. Defaults to pre-screening when omitted. Options — `pre-scr
seniority_level	string/null	no	Target seniority level for the role; auto-detected from the job description when omitted. Options — entry-level: Early-career or graduate roles. \| intermediate: Some experience required. \| `senior
result_view	string/null	no	Result screen shown to the candidate after finishing. With any value other than none, the candidate sees a results screen where they can provide feedback, record an intro video and edit the transcri
interview_conversation_speed	string/null	no	Conversation pace of the AI avatar. Omit/null keeps the template default pace. Options — slower: The avatar speaks more slowly — easier to follow for non-native speakers. \| normal: Default speakin
candidate_video_introduction	string/null	no	Whether a candidate video introduction is optional or required.
interview_tone	string/null	no	Interview tone — configures the AI avatar's speaking style and the tone of the AI-generated questions and follow-ups. Case-insensitive; omit to default to relaxed. Options — relaxed: Friendly and co
interview_length		no	Number of questions to generate (1-40). Also capped by max_duration, which allows one question per 2 minutes: 20 min -> 10 questions, 30 min -> 15, 45 min -> 22, 60 min -> 30, 80 min -> 40. Asking for
interview_attempts	number/null	no	Allowed candidate attempts (1-20).
max_duration	number/null	no	Maximum interview duration in seconds. Scopes how many questions are generated (see interview_length) and is stored on the interview as the live session limit and the basis for the credit multiplier.
max_followups	integer/null	no	Maximum number of AI follow-up questions. 0 disables follow-ups; presets are 0-3 (none/low/normal/high) and custom values start at 4; null uses the template default (Normal).

[Interviews] Create a new interview from an explicit array of questions. The AI rephrases your wording by default; pass interview_tone="exact" to have each question asked verbatim, which is what you want when the wording is a script (compliance, translated, or legally reviewed text). Creates a new interview definition set from a caller-provided array of questions, builds its default and generat

Parameter	Type	Required	Notes
name	string/null	yes	Interview/position name.
location	string/null	yes	Job location — a city/country, or remote. Required and must not be empty: when the job description gives no location, pass Not specified.
interview_template_id	string/null	yes	Id of the interview template to use. Must reference an existing interview_templates row.
mojito_language_code	string/null	yes	Platform language code (one of the platform-languages.json codes); must also resolve to a supported language with an Azure speech mapping.
description	string/null	yes	Short interview description.
status	string/null	yes	Lifecycle status of the interview. Options — draft: Created but not published — not visible to candidates and cannot be run yet. Use to stage an interview before going live. \| active: Published an
type	string/null	yes	Product type of the interview. Options — interview: Standard candidate interview for a role — answers are AI-scored and produce a hiring recommendation. \| coaching: Practice/coaching session — can
visibility	string/null	yes	Who can discover and access the interview. Options — merchant_public: Listed on the merchant's public interview list — anyone with the merchant link can find and start it. \| merchant_invite: Invit
questions	array/null	yes	Ordered list of interview questions to create as steps.
recording	string/null	no	Cheating/proctoring detection mode for candidate answers — this is NOT a full session recording. Video options also record the candidate. Omit/null to disable. Options — audio_first_5_answers: Audio
recording_full_session	string/null	no	Full interview-session recording (includes the avatar and voice) produced as a single file. Independent of recording. Omit/null to disable. Options — audio_all: Record the whole session audio (ava
environment	string/null	no	Which of your webhook environments results from this interview are delivered to. Defaults to production. Options — production: Live hiring. Results reach the webhooks configured as production. This
interview_type	string/null	no	Interview style — configures the AI avatar and the follow-up questions it generates during the interview. The base questions you supply are used as-is and are NOT affected by this setting. Options —
seniority_level	string/null	no	Target seniority level for the role; auto-detected from the job description when omitted. Options — entry-level: Early-career or graduate roles. \| intermediate: Some experience required. \| `senior
result_view	string/null	no	Result screen shown to the candidate after finishing. With any value other than none, the candidate sees a results screen where they can provide feedback, record an intro video and edit the transcri
interview_conversation_speed	string/null	no	Conversation pace of the AI avatar. Omit/null keeps the template default pace. Options — slower: The avatar speaks more slowly — easier to follow for non-native speakers. \| normal: Default speakin
candidate_video_introduction	string/null	no	Whether a candidate video introduction is optional or required.
interview_tone	string/null	no	Tone — configures the AI avatar's speaking style and the follow-up questions it generates; the base questions you supply are not affected. Case-insensitive; omit to default to relaxed. Options — `re
interview_attempts	number/null	no	Allowed attempts, 1-20.
questions_random_subset	number/null	no	Fraction of questions to randomly ask, between 0.01 and 0.9.

[Interviews] Create a role-play persona: an avatar that plays a defined role in a free-form conversation instead of a scored Q&A interview. FIRST CHOOSE portal, because it selects between two different products: portal="interview" builds a SIMULATED PERSONA a recruiter invites candidates to — scored, billed to merchant credits, and listed with the recruiter's other results; portal="coaching"

Parameter	Type	Required	Notes
name	string/null	yes	Persona / session name.
interview_template_id	string/null	yes	Id of the interview template (avatar) the persona uses.
mojito_language_code	string/null	yes	Platform language code used for the conversation. Must be one of the platform-languages.json codes.
status	string/null	yes	Lifecycle status of the interview. Options — draft: Created but not published — not visible to candidates and cannot be run yet. Use to stage an interview before going live. \| active: Published an
visibility	string/null	yes	Who can discover and access the interview. Options — merchant_public: Listed on the merchant's public interview list — anyone with the merchant link can find and start it. \| merchant_invite: Invit
description	string/null	no	Short persona description shown to the candidate on the pre-session poster. Candidate-visible — keep it to max 2 sentences. Unlike job-interview-create, personas run no AI generation, so this is never
persona_role_avatar	string/null	yes	The role the AI avatar plays. Candidate-visible — shown on the pre-session poster as 'Role of the agent', so write it as candidate-facing setup and keep it to max 2 sentences. Example: 'is to act as a
persona_role_user	string/null	yes	The role the candidate (mentee) plays. Candidate-visible — shown on the pre-session poster as 'Your role', so write it as candidate-facing setup and keep it to max 2 sentences. Example: 'is to be a sa
persona_avatar_who_is	string/null	no	Who the avatar represents: name, role, context, personality, woven with what drives them underneath (motive, fear, what they refuse until heard, what they do not know until told). One continuous descr
persona_avatar_knowledge	string/null	no	Private facts the avatar can use (numbers, dates, names, objections), plus any personal details shareable only after progress and only if natural — timing written inline, not as labelled subsections.
persona_avatar_end_conditions	string/null	no	When the avatar should end the session. Prefer referring to persona_avatar_progress: wrap up when progress is complete (turning point unlocked and a plan accepted, or steps "Done when" reached), or wh
persona_avatar_progress	string/null	no	How the conversation moves forward — one plain-text value starting with Mode: turning point (resistance) or Mode: steps (difficult conversation protocol), then the labelled lines for that mode (In
opening_line	string/null	no	The avatar's opening line — the FIRST thing it says out loud when the session starts, before the candidate has said anything. This is a literal spoken line, NOT a description: write the exact words th
candidate_expectations	string/null	no	Mentee assessment goals — free-text describing what the candidate is expected to achieve (max 2100 chars).
recording	string/null	no	Cheating/proctoring detection mode for candidate answers — this is NOT a full session recording. Video options also record the candidate. Omit/null to disable. Options — audio_first_5_answers: Audio
recording_full_session	string/null	no	Full interview-session recording (includes the avatar and voice) produced as a single file. Independent of recording. Omit/null to disable. Options — audio_all: Record the whole session audio (ava
environment	string/null	no	Which of your webhook environments results from this interview are delivered to. Defaults to production. Options — production: Live hiring. Results reach the webhooks configured as production. This
result_view	string/null	no	Result screen shown to the candidate after finishing. With any value other than none, the candidate sees a results screen where they can provide feedback, record an intro video and edit the transcri
interview_conversation_speed	string/null	no	Conversation pace of the AI avatar. Omit/null keeps the template default pace. Options — slower: The avatar speaks more slowly — easier to follow for non-native speakers. \| normal: Default speakin
candidate_video_introduction	string/null	no	Whether a candidate video introduction is optional or required.

[Interviews] Get the definition/configuration of an interview (position), including its ordered questions array. The questions come back in the same format create_interview_from_questions accepts, so you can read an interview here, change the array, and send it to update_interview. Each question's id identifies it — keep the ids you did not mean to change. Retrieves the interview definition f

Parameter	Type	Required	Notes
position_id	string	yes	Identifier of either an interview definition (single-stage) or a position definition (multi-stage). The function resolves whichever matches.
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Interviews] Update the configuration of an existing interview/position: name, description, avatar template, recording, scoring, tags and the rest of the create-time settings. Only the fields you send are changed. To change the questions, send questions — the WHOLE list you want the interview to end up with, in order, in the format get_interview_definition returns. OMIT questions and the exist

Parameter	Type	Required	Notes
position_id	string/null	yes	Id of the interview definition (single-stage) or position definition (multi-stage) to update. The same id you pass to job-interview-get.
status	string/null	no	New lifecycle status. Applied through the same interview_set_status routine as job-interview-set-state (which is also where you manage the iframe embed key).
visibility	string/null	no	Who can discover and access the interview. Options — merchant_public: Listed on the merchant's public interview list — anyone with the merchant link can find and start it. \| merchant_invite: Invit
environment	string/null	no	Which of your webhook environments results from this interview are delivered to. Defaults to production. Options — production: Live hiring. Results reach the webhooks configured as production. This
name	string/null	no	Interview / position name.
code	string/null	no	External code/reference. Blank is stored as null.
location	string/null	no	Interview location (column interview_location). Blank is stored as null.
cover_image_url	string/null	no	Cover image URL.
description	string/null	no	Short interview description.
description_long	string/null	no	Long-form interview description (column interview_description_long). Rendered as Markdown on the candidate-facing position page, including chips, callouts, cards, columns and buttons — formatting gu
interview_department	string/null	no	Department the position belongs to. Blank is stored as null.
interview_salary	string/null	no	Salary range shown for the position. Blank is stored as null.
interview_available_till	string/null	no	ISO date/time after which the interview is no longer available to candidates. null keeps it always available.
recruiter_profile_id	string/null	no	Profile id of the recruiter owning this interview. Must be a merchant/merchant_owner/admin profile of the same merchant. null clears it.
candidate_notification_channel	string/null	no	SMS / WhatsApp notifications to the candidate, sent alongside the e-mails: "reminders" = with both e-mail reminders (day 1 and day 3); "last_reminder" = only with the final day-3 reminder; "all" = inv
country_availability	object/null	no	Which countries the interview / position is open to on the candidate portal, judged by the IP address the candidate opens it from (an unknown location only passes when countries_allowed / countries_al
tags	array/null	no	Free-form tags stored on the interview. Tags are also the coaching-catalogue mapping key: a catalogue directory (see the catalogue-tag-create / catalogue-tag-update endpoints) lists a coaching or pers
questions	array/null	no	OPTIONAL. Omit this field entirely and the interview's questions are left exactly as they are — this endpoint only touches questions when you send the array. When you do send it, send the COMPLETE lis
regenerate_candidate_expectations	boolean/null	no	Re-derive the interview-level candidate_expectations_json scoring rubric from the resulting question list, the way job-interview-create-from-array derives it at creation time. Only applies when `que
type	string/null	no	Product type of the interview. Changing it also re-derives type_credit (null for interview/assessment, otherwise interview_coach_manager) unless you send type_credit explicitly. Single-stage inter

[Interviews] Change the state of an interview/position (e.g. open, closed). Changes the lifecycle status of an interview or position (draft, active, archived, preparing, completed, deleted) and/or manages its embed key. Provide at least one of status or is_embedded.

Parameter	Type	Required	Notes
position_id	string/null	yes	Interview definition id or position id whose state should change.
status	string/null	no	New lifecycle status to apply.
is_embedded	boolean/null	no	Controls iframe embedding of the interview on an external page. When true, ensures an embed key exists (returns embed_id/embed_signing_key, used to authenticate/sign the iframe embed). When false, rem
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Interviews] Generate a signed public interview URL/token. Generates a public, token-signed URL for an existing interview, profile, or result. The required id fields depend on type.

Parameter	Type	Required	Notes
type	string/null	yes	Which kind of signed URL to generate.
merchant_id	string/null	no	Override merchant id (admin / sub-merchant only).
interview_profile_id	string/null	no	Candidate profile id. Required for interview-for-profile and results-for-profile.
interview_id	string/null	no	Interview or position id. Required for interview-for-profile and interview-results-for-position.
interview_result_id	string/null	no	Interview result id. Required for interview-result-candidate and interview-result-talent-seeker.
hide_menu		no	Pass the string 'false' to show the navigation menu; any other value hides it (default).
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Interviews] Register users/candidates for a specific interview and return their personal interview links. Registers (or updates) one or more candidate profiles for an interview and returns a one-time interview URL for each. Accepts a Supabase user JWT (merchant/admin) or the service key (merchant_id then required).

Parameter	Type	Required	Notes
users	array/null	yes	Candidates to register for the interview. Each gets a one-time interview URL.
interview_id	string/null	yes	Interview definition (interview_def_set) or position (position_def_set) id to register users for.
merchant_id	string/null	no	Merchant id. Required when authenticating with the service key; for user tokens it is optional and only honored for admin / sub-merchant accounts.
send_email	boolean/null	no	Whether to send an invitation email to each registered candidate.
hide_menu		no	When true (or the string "true"), the interview UI hides its menu (view_hm).
hide_iframe		no	When true (or the string "true"), the interview UI hides its iframe chrome (view_hi).
is_test		no	When true (or the string "true"), mints a test token that can take a draft/unpublished interview and flags the result as a test. For a DRAFT interview it also recompiles the definition (interview_reca
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Interviews] List the merchant's interview definitions. Paginated list of a merchant's interview definitions (the admin-portal interview list), scoped to your token's merchant (or a merchant_id override). Capped at 1000 records per page.

Parameter	Type	Required	Notes
merchant_id	string	no	Optional merchant to scope to. Admins and sub-merchant operators only; other callers always use their token's merchant.
type	string	no	Product type of interviews to list.
status	string	no	Filter by lifecycle status. Omit to include all statuses.
show_public	string	no	Include interviews shared publicly across merchants (coaching/avatars).
show_demo	string	no	Include demo/sample interviews.
filter_text	string	no	Case-insensitive search on the interview name.
filter_emoji	string	no	Filter by the interview emoji marker.
limit	integer	no	Maximum number of records to return (1–1000).
offset	integer	no	Number of records to skip from the start of the result set.
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Coaching catalogue] Create a directory (page) in the coaching portal catalogue. A directory nests other directories (tags_sub), lists coaching sessions whose own tags match its tags_interview_set_filter, and can carry a fully custom Markdown page (content_md) with [sessions], [directory:…], [session:…] and [plan-progress] directives. One directory can hold several languages: the t

Parameter	Type	Required	Notes
id	string/null	yes	Directory id — also the catalogue URL segment (/catalogue/<id>) and the value other directories reference in their tags_sub. Lowercase letters, digits and single - or _ separators. Convention is to
name	string/null	yes	Display name of the directory, shown as the page title and on its card.
description	string/null	no	Short description shown on the directory card.
mojito_language_code	string/null	no	Language of the directory (one of the platform-languages.json codes). The catalogue groups directories by language; defaults to en when omitted.
visibility	string/null	no	Who can see the catalogue directory. Options — public: Shared across every merchant. Platform admins only — a merchant caller is rejected by row-level security. \| merchant_public: Listed in the me
status	string/null	no	Lifecycle status of the catalogue directory. Options — draft: Not published — the directory exists but is not served to visitors. \| active: Published and served in the catalogue. \| archived: Ret
cover_image_url	string/null	no	Cover image URL shown on the directory card.
coach_plan	string/null	no	Coaching-plan stage this item belongs to, used by the coaching-plan progress view. Omit/null to leave it out of any plan. Options — demo: Demo session. \| screening: Screening-interview practice. \|
tags_sub	array/null	no	Ids of the directories nested under this one, in display order. Replaces the whole list — send the full set, not just the additions. A referenced directory only appears if it exists and is visible to
tags_interview_set_filter	array/null	no	Tag filter selecting which coaching sessions this directory lists: a session appears when its own tags contain EVERY tag here (an AND, not an OR). Only active coaching/persona sessions with visibi
content_md	string/null	no	Markdown for a custom directory page. When set (even as an empty string) the markdown replaces the default grid and decides the layout itself; null renders the plain grid of sub-directories and sessio
translations	object/null	no	Other language versions of the directory, keyed by mojito language code. The top-level fields are the default language (mojito_language_code); each version is a page of its own (name, Markdown, sess
parent_tag	string/null	no	Id of an existing directory to nest this new one under: the new id is appended to that directory's tags_sub. Omit to create a top-level directory (reachable via a direct link, or by adding it to ano
merchant_id	string/null	no	Merchant that owns the directory. Admin / sub-merchant callers only; otherwise taken from your token.
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Coaching catalogue] Update a coaching catalogue directory: rename it, change which sessions it lists (tags_interview_set_filter), re-order its sub-directories (tags_sub), author its custom Markdown page (content_md), or add, replace or remove a language version (translations, per language; null removes one). Only the fields you send are changed. Coaching-platform feature. Updates a direc

Parameter	Type	Required	Notes
id	string/null	yes	Id of the directory to update (the catalogue URL segment). The id itself is not changed here — rename a directory in the admin catalogue editor, which moves every link to it.
name	string/null	no	Display name of the directory.
description	string/null	no	Short description shown on the directory card.
mojito_language_code	string/null	no	Language of the directory (one of the platform-languages.json codes). The catalogue groups directories by language.
visibility	string/null	no	Who can see the catalogue directory. Options — public: Shared across every merchant. Platform admins only — a merchant caller is rejected by row-level security. \| merchant_public: Listed in the me
status	string/null	no	Lifecycle status of the catalogue directory. Options — draft: Not published — the directory exists but is not served to visitors. \| active: Published and served in the catalogue. \| archived: Ret
cover_image_url	string/null	no	Cover image URL shown on the directory card. null clears it.
coach_plan	string/null	no	Coaching-plan stage this item belongs to, used by the coaching-plan progress view. Omit/null to leave it out of any plan. Options — demo: Demo session. \| screening: Screening-interview practice. \|
tags_sub	array/null	no	Ids of the directories nested under this one, in display order. Replaces the whole list — send the full set, not just the additions. A referenced directory only appears if it exists and is visible to
tags_interview_set_filter	array/null	no	Tag filter selecting which coaching sessions this directory lists: a session appears when its own tags contain EVERY tag here (an AND, not an OR). Only active coaching/persona sessions with visibi
content_md	string/null	no	Markdown for the custom directory page. Sending null removes the custom page and restores the default grid; sending a string replaces the whole page. Directives, each ALONE on its own line: `[plan-pro
translations	object/null	no	The directory's OTHER language versions, keyed by mojito language code. The top-level fields are the default language (mojito_language_code); each version here is a page of its own with its own name
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Coaching catalogue] Read one catalogue directory in full: its settings, its custom Markdown page (content_md), its resolved sub-directories, and the coaching sessions its tag filter currently matches — which is how you verify that a session's tags actually place it in this directory. Read before updating: content_md, tags_sub and tags_interview_set_filter are replaced wholesale, so you

Parameter	Type	Required	Notes
id	string	yes	Id of the catalogue directory to read (the catalogue URL segment). The old id of a renamed directory also works; the response carries its current id.
merchant_id	string	no	Optional merchant to scope to. Admins and sub-merchant operators only; other callers always use their token's merchant.
mojito_language_code	string	no	Show sub_directories and matched_sessions for this language version of the directory (one of its languages) instead of the default one - how you verify a translation lists the right sessions.
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Coaching catalogue] List the coaching-catalogue directories you can see (your merchant's own plus the platform-wide public ones). Start here to find a directory id, to pick a parent for a new one, or to walk the tree with parent_tag; is_start_directory marks the page the catalogue opens on. The custom Markdown page is not included — read it with get_catalogue_directory. Returns 25 at a time;

Parameter	Type	Required	Notes
merchant_id	string	no	Optional merchant to scope to. Admins and sub-merchant operators only; other callers always use their token's merchant.
status	string	no	Filter by lifecycle status. Omit to include every status you can see (deleted directories are never returned).
visibility	string	no	Filter by visibility.
mojito_language_code	string	no	Filter by language: directories whose default language or one of whose language versions is this one. Omit for all languages.
filter_text	string	no	Case-insensitive search on the directory id, name and description.
parent_tag	string	no	Return only the directories nested directly under this one (its tags_sub), in the parent's own order. Combine with the other filters to narrow further.
include_public	string	no	Include the platform-wide public directories shared across merchants.
limit	integer	no	Maximum number of records to return (1–1000).
offset	integer	no	Number of records to skip from the start of the result set.
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Results] Get full interview result details including transcript and scores. Scores are assistive output for a human reviewer. One result is a large record, so view controls how much of it comes back — the default (standard) omits only the raw machine assessment data. Returns an interview result with its full transcript and AI assessment. Optionally attaches signed recording URLs.

Parameter	Type	Required	Notes
interview_result_id	string	yes	The interview result to fetch the transcript and details for.
get_signed_recordings	string	no	When true, includes short-lived signed recording URLs for the session, the video introduction, and each transcript answer.
view	string	no	How much of the record to return. Handled by the MCP server, not the JobMojito API — it only narrows the response, never the query. - summary: scores, the overall AI analysis, and each question wit
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Results] Generate an interview result report (HTML/PDF/JSON) for a completed interview. The report is decision-support material for a human reviewer, not an automated hiring decision. Generates an interview result report as a PDF (returns a signed URL), raw HTML, or structured JSON. Provide either interview_result_id for a single result or interview_result_ids for a combined multi-result rep

Parameter	Type	Required	Notes
interview_result_id	string/null	no	—
interview_result_ids	array/null	no	Generate a single combined report for multiple results.
export_type	string/null	yes	—
export_features_result	object	no	—
template		no	—
store_file	boolean/null	no	When true (pdf only), persist the file to storage and return a signed URL.
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Results] Re-open a submitted interview result so the candidate can retry. Marks a submitted (active + completed) interview result as unsuccessful so the candidate can retake it. Resets the result to draft and clears the recruiter decision.

Parameter	Type	Required	Notes
interview_result_id	string/null	yes	The interview result to reopen for another attempt.
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Results] List the merchant's interview results. Rows carry the candidate's scores and recruiter risk flags, so this returns 20 at a time; page with offset while pagination.has_more is true, or narrow with tab/interview_id/filter_text. Paginated list of a merchant's interview results (the admin-portal results list), scoped to your token's merchant (or a merchant_id override). Capped at

Parameter	Type	Required	Notes
merchant_id	string	no	Optional merchant to scope to. Admins and sub-merchant operators only; other callers always use their token's merchant.
type	string	no	Product type of results to list.
tab	string	no	Filter by decision/completion state. Omit (or empty) to include all.
step	string	no	Filter by pipeline step type (pre-screening, interview or meeting). Omit for all.
interview_id	string	no	Filter to a single interview definition id.
profile_interview_id	string	no	Filter to a single candidate (profile_interview) id.
risks	string	no	Comma-separated list of recruiter-risk keys to filter by (matches any).
order_by	string	no	Sort order of the result set.
filter_text	string	no	Case-insensitive search on candidate name or email.
filter_emoji	string	no	Filter by the candidate emoji marker.
limit	integer	no	Maximum number of records to return (1–1000).
offset	integer	no	Number of records to skip from the start of the result set.
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Results] Get the merchant's daily event analytics. Daily event-count time-series for a merchant over a date range (the admin-portal analytics events graph), scoped to your token's merchant (or a merchant_id override). Optionally drilled to a single interview. Capped at 1000 records per page. Note: only day/event combinations with a non-zero count are returned — any day/event pair absent from the

Parameter	Type	Required	Notes
merchant_id	string	no	Optional merchant to scope to. Admins and sub-merchant operators only; other callers always use their token's merchant.
date_from	string	yes	Start of the date range (inclusive), YYYY-MM-DD.
date_to	string	yes	End of the date range (inclusive), YYYY-MM-DD.
interview_id	string	no	Optional interview (interview_def_set) or position (position_def_set) id to drill the event counts down. The type is detected automatically: a position aggregates the daily counts across every intervi
limit	integer	no	Maximum number of records to return (1–1000).
offset	integer	no	Number of records to skip from the start of the result set.
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Results] Get the merchant's credit usage. Per-event credit-usage ledger for a merchant: every billable analytics event (interview, pre-screening, public avatar, simulation, …) that consumed credits, ordered most recent first. Scoped to your token's merchant, or a merchant_id override for admins / sub-merchant operators. The credits consumed by each event are in stats.credit_amount. Capped at 100

Parameter	Type	Required	Notes
merchant_id	string	no	Optional merchant to scope to. Admins and sub-merchant operators only; other callers always use their token's merchant.
interview_id	string	no	Optional interview (interview_def_set) or position (position_def_set) id to drill the credit-usage ledger down to a single interview or position. The type is detected automatically: for a position the
limit	integer	no	Maximum number of records to return (1–1000).
offset	integer	no	Number of records to skip from the start of the result set.
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Reports] List what a custom report can use on this account: datasets (interview results, invitations, position pipeline, ATS pipeline, credits, coaching sessions - only those the account and your role include), their dimensions (group by / conditions, with allowed values) and measures. Call this first: a report definition may only use ids listed here. Custom reports are switched on per account by

Parameter	Type	Required	Notes
merchant_id	string	no	Optional merchant to scope to. Admins and sub-merchant operators only; other callers always use their token's merchant.
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Reports] List custom reports you can open (yours, shared with you) and the JobMojito templates, with id, title, visibility, your access and version. Custom reports you can open on this account (yours, the ones shared with you) and the JobMojito templates. Pinned first, then most recently updated.

Parameter	Type	Required	Notes
merchant_id	string	no	Optional merchant to scope to. Admins and sub-merchant operators only; other callers always use their token's merchant.
scope	string	no	all (default), mine, shared (by colleagues) or templates.
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Reports] Get a custom report's JSON definition, visibility, your access and its version. Read it before update_report: the definition is replaced whole and the version must match. The report's JSON definition, visibility, your access (owner, edit, view) and its version (needed to update it). People who can edit also get the unpublished draft, if any.

Parameter	Type	Required	Notes
merchant_id	string	no	Optional merchant to scope to. Admins and sub-merchant operators only; other callers always use their token's merchant.
id	string	yes	Report id (from list_reports).
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Reports] Run a saved custom report and return each block's rows (aggregated numbers, at most 500 rows per block). Optional filters JSON overrides the period / positions / interviews for this run only. Report numbers are decision-support material for a human reviewer. Runs every block of a saved report and returns its rows. Filters start from the report's defaults, then your own saved filters,

Parameter	Type	Required	Notes
merchant_id	string	no	Optional merchant to scope to. Admins and sub-merchant operators only; other callers always use their token's merchant.
id	string	yes	Report id (from list_reports).
filters	string	no	Optional JSON ReportFilters to apply on top, e.g. {"period":{"preset":"last_month"}}.
block_id	string	no	Run only this block.
draft	string	no	Run the unpublished draft instead (only if you can edit the report).
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Reports] Validate a report definition against the catalogue and run it without saving anything. Use it before create_report / update_report: a block that is wrong comes back with ok=false and an error naming the field and the valid ids. Validates a report definition against the catalogue and runs it, without storing anything. Use it to check a definition before create_report or update_report. A

Parameter	Type	Required	Notes
merchant_id	string/null	no	Optional merchant to act on. Admins and sub-merchant operators only; other callers always use their token's merchant.
definition	object	yes	A custom report: report-wide filters and up to 12 blocks. Read report-catalog first for the dataset, field and measure ids.
filters		no	—
block_id	string/null	no	Run only this block.
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Reports] Save a new custom report from a definition (schema jobmojito.report/v1). It is created as Only me: tell the user they can share it from the returned admin_url. Check the definition with preview_report first. Stores a new custom report. It is created as "Only me" (private to you); share it from the JobMojito admin. Returns its id, version and the admin link to open it. Check the definiti

Parameter	Type	Required	Notes
merchant_id	string/null	no	Optional merchant to act on. Admins and sub-merchant operators only; other callers always use their token's merchant.
definition	object	yes	A custom report: report-wide filters and up to 12 blocks. Read report-catalog first for the dataset, field and measure ids.
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Reports] Replace a custom report's definition (send the whole definition and the version from get_report). On a report shared with other people the change is saved as a draft that the owner publishes in the admin; a private report updates at once. Replaces the definition of a report you own or may edit. Send the version you read; if someone changed the report since, you get 409 and should get it

Parameter	Type	Required	Notes
merchant_id	string/null	no	Optional merchant to act on. Admins and sub-merchant operators only; other callers always use their token's merchant.
id	string/null	yes	Report id (from list_reports).
version	integer/null	yes	The version you read (get_report / list_reports). A stale version is refused with 409.
definition		yes	—
target	string/null	no	published (default) or draft. A private report always publishes. Through the MCP server a shared report always gets a draft that its owner publishes in the admin.
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Candidates] List the merchant's candidates. Paginated list of a merchant's candidates (the admin-portal candidates list), scoped to your token's merchant (or a merchant_id override). Capped at 1000 records per page.

Parameter	Type	Required	Notes
merchant_id	string	no	Optional merchant to scope to. Admins and sub-merchant operators only; other callers always use their token's merchant.
tab	string	no	Filter candidates by recent activity. Omit (or empty) to include all.
source	string	no	Filter by how the candidate entered: invited or self-registered. Omit for both.
order_by	string	no	Sort order of the result set.
filter_text	string	no	Search on candidate name, email, external id, phone and CV skills. Every word must match (case and accents ignored; longer words tolerate typos). Without order_by, the best matches come first.
filter_emoji	string	no	Filter by the candidate emoji marker.
limit	integer	no	Maximum number of records to return (1–1000).
offset	integer	no	Number of records to skip from the start of the result set.
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Knowledge base] Upload and process a knowledge base document (multipart form-data). Uploads a document to a knowledge base store and queues it for processing. Accepts the file either as multipart/form-data (binary file) or as application/json (base64 file).

Parameter	Type	Required	Notes
knowledge_base_store_id	string/null	yes	The knowledge base store to add the document to.
name	string/null	no	Document name (with extension). Falls back to the uploaded file name for multipart.
merchant_id	string/null	no	Override merchant id (admin / sub-merchant only).
file	string/null	yes	The document file (binary).
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Admin] List sub-merchants under the merchant account. Paginated list of the sub-merchants the caller administers (the admin-portal sub-merchants list). Visibility is enforced by row-level security. Capped at 1000 records per page.

Parameter	Type	Required	Notes
merchant_id	string	no	Optional merchant to scope to. Admins and sub-merchant operators only; other callers always use their token's merchant.
order_by	string	no	Sort order of the result set.
filter_text	string	no	Case-insensitive search on the sub-merchant name.
limit	integer	no	Maximum number of records to return (1–1000).
offset	integer	no	Number of records to skip from the start of the result set.
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Admin] List available avatar/voice templates. Each item's type decides the interview modality: interactive_elevenlabs = voice-only (no video avatar); interactive_spatius = realtime interactive 3D avatar (rendered in the candidate's browser, 1.25 credits, no early stop); interactive_heygen = premium realtime interactive video avatar; offline_heygen = pre-recorded, non-interactive avatar.

Parameter	Type	Required	Notes
merchant_id	string	no	Optional merchant to scope to. Admins and sub-merchant operators only; other callers always use their token's merchant.
type	string	no	Filter by avatar template type. Omit for all.
status	string	no	Filter by status. Omit for all except archived (see include_archived).
mojito_language_code	string	no	Filter by platform language code. Omit for all languages.
filter_text	string	no	Case-insensitive search on template name or voice language name.
include_archived	string	no	Include archived templates (excluded by default).
include_public	string	no	Also include public templates shared across merchants, in addition to this merchant's own.
limit	integer	no	Maximum number of records to return (1–1000).
offset	integer	no	Number of records to skip from the start of the result set.
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Admin] Get a merchant status snapshot: credit balances, subscription, pending-work counts, candidate/result totals, and invitation headroom. Status snapshot for a merchant: interview-credit balances, subscription type/status, pending-work counts (undecided / ongoing / uncredited interviews), candidate & result totals with 14-day history, and invitation headroom. Scoped to your token's merchant (

Parameter	Type	Required	Notes
merchant_id	string	no	Optional merchant to scope to. Admins and sub-merchant operators only; other callers always use their token's merchant.
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Admin] List supported platform (mojito) languages: the code to pass as mojito_language_code, English/local names, SVG flag URL, per-interface enablement flags, and Azure speech accents. Returns all supported platform (mojito) languages: the mojito language code, English and local names, and an SVG flag image URL. Use the code as mojito_language_code when creating interviews or personas.

Parameter	Type	Required	Notes
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Feedback] Send a feature request to the JobMojito product team. It is posted on the public feature request board under the signed-in user's name, where they get status updates; the company is not named. Write a short title and a description of the need and why (no candidate data or company names). Confirm the wording with the user before submitting; at most 5 a day. Sends a feature request to th

Parameter	Type	Required	Notes
title	string/null	yes	A short summary of the feature, shown as the post title.
description	string/null	yes	What the user needs and why: the problem, how they work around it today, who it would help. Plain text; blank lines separate paragraphs. The board is public: do not include candidate data, company nam
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

[Feedback] Report a technical problem to JobMojito support. It opens a support conversation from the signed-in user's account (their e-mail), with their company and the interview or result ids given; support answers there. Describe what was done, what was expected and what happened (error text as shown). Confirm the wording with the user first; at most 5 a day. Reports a technical problem to JobM

Parameter	Type	Required	Notes
description	string/null	yes	What went wrong: what you did, what you expected, what happened instead (error messages as shown), and since when. Plain text; blank lines separate paragraphs. Do not include passwords or API keys.
interview_id	string/null	no	The interview (definition) the problem is about, if any.
result_id	string/null	no	The interview result the problem is about, if any.
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

Show the interactive JobMojito merchant picker (UI). ALWAYS call this when the user wants to choose, switch, or set a merchant, or when a tool needs a merchant_id and none is selected. It renders a searchable picker with clickable options. Do NOT list merchants as text or ask the user to type a name — render this picker instead. After calling it, STOP and wait for the user's selection; then pas

Parameter	Type	Required	Notes
conversation_id	string	no	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep

Free

$0 forever

Every tool — any call limit is its publisher’s, not ours
No card, and mcprush charges nothing for it
Runs at its publisher’s own address — this marketplace is not in the path
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install JobMojito or to call it, at any volume.

ATool-list grade · score 93 / 100

Release 1.3.2 · scanned 20 Oct 2026

Graded from the tools this server lists, not from its source code.

Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.

Threat score100

Client score93

Findings0 threat · 8 capability

Capabilitymoderate

Coveragemanifest

Verificationnot in this report

Surface digeste1afce23d1f8add5b542e87cdd144946c67817430c9bed4de63db82aedd00a8d

Score vectorthreat 100 → client 93

Term	Level	What it prices	Points
capability-exposure	moderate	capability blast radius (moderate) — client exposure if the model is manipulated	−3
coverage-honesty	manifest	inspection depth (manifest) — how much of the target the scan could see	−4

score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.

What the scan could actually read

A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.

The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.

Tool surfaceread

Implementation sourcenot available

Package metadatanot available

Live transportnot available

The implementation source was not read — this reflects the declared tool metadata only.

Capability — what it could do if the model were manipulated

Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.

Tool	Capability tags	Why the tag was assigned
search_documentation	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
get_documentation	untrusted-input	untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server)
list_my_merchants	no tags
create_interview	external-sink	external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true
create_interview_from_questions	external-sink	external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true
create_persona	external-sink	external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true
get_interview_definition	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
update_interview	external-sink	external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true
set_interview_state	external-sink	external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true
generate_interview_url	external-sink	external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true
register_users_for_interview	external-sink	external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true
list_interviews	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
create_catalogue_directory	external-sink	external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true
update_catalogue_directory	external-sink	external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true
get_catalogue_directory	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
list_catalogue_directories	untrusted-input	untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server)
get_interview_result_details	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
generate_interview_report	external-sink	external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true
request_another_interview_attempt	external-sink	external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true
list_interview_results	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
get_merchant_analytics	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
get_merchant_credit_usage	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
list_report_fields	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
list_reports	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
get_report	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
run_report	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
preview_report	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
create_report	external-sink	external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true
update_report	external-sink	external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true
list_candidates	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
upload_knowledge_base_document	external-sink	external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true
list_sub_merchants	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
list_avatars	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
get_merchant_status	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
list_languages	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)
submit_feature_request	external-sink	external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true
report_technical_issue	external-sink	external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true
jobmojito_configuration	no tags

Toxic-flow graph

The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.

flow-1

Untrusted input can drive an external action even though no sensitive source is exposed.

Supply chain and provenance

Integrityfirst-seen

Surface digeste1afce23d1f8add5

Scanned2026-10-20

This is the first scan of this surface here, so there is nothing yet to compare it against.

Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.

Where are you running it?

Tool surface

Release history

JobMojito MCP

What it does

Quickstart

Where are you running it?

Tool surface

What counts against your monthly calls

What the scan could actually read

Capability — what it could do if the model were manipulated

Toxic-flow graph

Supply chain and provenance

Release history

See also