Google Search Console integration for Model Context Protocol (MCP)
Nothing to run from here
GEN is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
90/100
tool-list score
1
downloads a day
remote
at its publisher
18
downloads in 30d
What it does
GEN is the creative AI video engineer. Free editor/social publishing; AI credits via card/x402.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http gen-mcp https://mcp.gen.pro --header 'X-API-Key: ${X_API_KEY}'
# 2 — ask your agent for something these tools do
# gen_agent_action, gen_analyze, gen_ask and 16 more
It needs X_API_KEY (Optional GEN PAT for clients without OAuth. Existing users: gen.pro/api. Agents: gen.pro/skill.md. Leave empty when using OAuth): this sends it in the X-API-Key header from your environment, so export it first — its endpoint answers 401 without it.
GEN costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
POAll 1 server
poweredbyGEN1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it. Claude Code reads X_API_KEY (Optional GEN PAT for clients without OAuth. Existing users: gen.pro/api. Agents: gen.pro/skill.md. Leave empty when using OAuth) from your environment each time it connects and sends it in the X-API-Key header — its endpoint answers 401 without it — so the key stays out of its config: export it in your shell profile (macOS, Linux), or run setx X_API_KEY … and open a new terminal (Windows).
claude mcp add --scope user --transport http gen-mcp https://mcp.gen.pro --header 'X-API-Key: ${X_API_KEY}'Reconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add — but its publisher asks for a key of their own on every call.
What it asks of you
Nothing is required, but it can take X-API-Key header (Optional GEN PAT for clients without OAuth. Existing users: gen.pro/api. Agents: gen.pro/skill.md. Leave empty when using OAuth.) if you want to set it.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
19 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Manage assistants and their profiles. One call carries one or more typed actions: set_profile (flat brand_name | description | competitors | identity_type | goal | target_platforms | shortform | longform | look | personality | persona_inspirations | research_topics | content_themes | monitored) | set_name (name) | set_location (catalog_version + country_code + city_id, sent alone) | set_primary_vo
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | no | The agent ID that owns the assistant; merged into each action exactly where the legacy tool accepts it | |
| actions | array | yes | One or more typed agent actions: set_profile (brand_name, description, competitors, identity_type, goal, target_platforms, shortform, longform, look, personality, persona_inspirations, research_topics |
| confirm_token | no | Single-use token from a CONFIRMATION_REQUIRED error; repeat the same call with it to complete the destructive action it was issued for. Omit on the first call. |
Analyze real social data and research the web: collect is the typed collection seam — one synchronous DW /collect call per request, answered as model-visible evidence + a per-target coverage summary + result cards (never a job id, never PENDING). For a request to analyze N videos, use collect with count:N and enrich:"full"; listing or showing posts leaves enrich omitted. Omitted enrich collects po
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | string | yes | The agent ID that owns the workspace (envelope; the billing subject — the analysis run is billed to this agent, no anonymous path) |
| actions | array | yes | One or more typed analysis actions: collect (the typed collection seam — targets [{platform, scope, target}] over scope user|hashtag|keyword|search|url|id|asset|account|creators|comments|sounds|ads an |
Ask GEN anything in plain words: a question, or a build goal for the composer. gen_ask is for durable multi-step work and scheduled or recurring work: GEN plans it, pauses for approval and keeps it in one conversation. For a single action, call that action's typed tool directly. A chat sent without a conversation_id starts one; the result returns conversation_id and request_id, so send that conver
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | no | The agent ID the conversation, ideas and research belong to (envelope; routed per branch) | |
| actions | array | yes | One or more typed ask actions: ask (question, optional conversation_id/wait/attachments/client_message_id) | chat (message, optional conversation_id/wait/attachments/client_message_id/metadata) | stee |
| confirm_token | no | Single-use token from a CONFIRMATION_REQUIRED error; repeat the same call with it to complete the destructive action it was issued for. Omit on the first call. |
Manage the agent's asset library: analyze any asset_id or file url with kind video/image/audio (quoted, confirmed DW enrichment; documents are refused until DW supports them; cached repeats are free), poll the job with gen_discover domain=asset view=analysis, or upload a file in two steps (create_direct_upload, then complete_asset_upload with the signed_id), import a public video URL (import_asset
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | no | The agent ID that owns the asset library (envelope; routed per branch) | |
| actions | array | yes | One or more typed asset actions: analyze (kind, exactly one asset_id or url) | create_direct_upload (filename, byte_size, checksum, content_type) | complete_asset_upload (signed_id, optional folder_id |
| confirm_token | no | Single-use token from a CONFIRMATION_REQUIRED error; repeat the same call with it to complete the destructive action it was issued for. Omit on the first call. |
Open a Stripe payment page for a workspace plan or credit pack with open_checkout (organization_id, credit_plan_id from billing.plans). Use open_checkout when the user asks to open checkout or subscribe to a plan; it creates a payment link and never charges a saved card. Do not use gen_sign_in_link for checkout: Stripe needs no GEN sign-in. prepare_funding_recovery (agent_id) returns the ready, no
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | no | The agent ID that owns the workspace (envelope; routed per branch) | |
| actions | array | yes | Typed billing actions: open_checkout (organization_id, credit_plan_id, optional success_url/cancel_url; creates a Stripe payment page without charging), list_owned_subscriptions (no fields) | list_own |
| confirm_token | no | Single-use token from a CONFIRMATION_REQUIRED error; repeat the same call with it to complete the destructive action it was issued for. Omit on the first call. |
Characters: one person each, with looks (images of the person) and talking characters (talking videos of the person with their voice, generated from a look or uploaded). For 'create a character', op=create is the first call — do not list characters or read gen_discover agent.profile_photos first (those are the agent profile photos, not characters). Reads (a viewer is enough): list (source my | lib
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | string | yes | The selected agent ID |
| op | no | The character op (list is the default only when no op-specific argument is given) | |
| source | string | no | Character pool (list): the agent's own characters (my), the shared character library (library), or both (all) |
| query | no | Text to search character names for (list) | |
| ready_for | no | list/get only: visual requires attached look or talking media; speaking also requires the saved primary voice. list excludes incomplete identities; get returns an actionable INPUT_NOT_READY refusal. O | |
| build_inputs | no | validate_cast only: persisted idea inputs, including cast/resolved_input/confirmed. Checks selected character media and voice requirements without starting or billing a build. | |
| character_id | no | Character ID (or its public id) from op=list (every op except list and create) | |
| look_id | no | Look ID from op=get (create_talking_character, delete_look; with rename, renames that look) | |
| talking_character_id | no | Talking character ID from op=get (get_talking_character, edit_talking_character, delete_talking_character; with rename, renames that talking character) | |
| name | no | Name (rename: required; create: optional, default the file name; upload_look, upload_talking_character, create_talking_character, edit_talking_character: optional, Rails picks a default) | |
| content_resource_id | no | Image or video content resource ID, or a completed image generation's receipt (generation:<job>:succeeded:<resource>) (create: an image becomes the original look; a video an uploaded talking character | |
| clone_voice | no | create with a video, upload_talking_character: clone the person's voice from the video's audio into the character's primary voice (a paid job). create: default true, false skips it, true refuses a vid | |
| voice_gender | no | create with a video, upload_talking_character with clone_voice: the cloned voice's gender label (default female) | |
| voice_language | no | create with a video, upload_talking_character with clone_voice: the cloned voice's language (default english) | |
| clips | no | 3 to 10 clips in order (create_talking_character, edit_talking_character): each {prompt, duration} with duration 5 or 10 seconds (default 10); on edit, {from_position} keeps that clip of the source ta | |
| aspect_ratio | no | Talking character shape (create_talking_character: default 9:16; edit_talking_character: default the source's) | |
| voice | no | set_primary_voice, and the voice create_talking_character / edit_talking_character speak with (default: the character's primary voice): {voice_id, provider} from gen_discover voice.mine or voice.list; | |
| script | no | What the talking character says (create_talking_character, edit_talking_character). Optional: a default line is used when blank | |
| confirm_token | no | Single-use token from a CONFIRMATION_REQUIRED error; repeat the same call with it to complete the destructive action it was issued for. Omit on the first call. | |
| idempotency_key | no | Stable retry key (sent as the Idempotency-Key header, max 255 chars). Reuse the same key when retrying this exact create so Rails replays the originally created resource (same id) instead of creating |
Manage an agent's content: its content resource files — create one from an uploaded file (create_content_resource), rename one (update_content_resource), or permanently delete one (delete_content_resource) — and its content ideas. generate_ideas is the content-ideas handshake: its first call answers needs_input (the fields to supply), a proposal (proposal_id + summary + plan) or running; reply wit
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | no | The agent ID that owns the content resources (envelope; routed per branch) | |
| actions | array | yes | One or more typed content actions: create_content_resource (signed_id, optional asset_folder_id) | update_content_resource (resource_id, filename) | delete_content_resource (resource_id) |
| confirm_token | no | Single-use token from a CONFIRMATION_REQUIRED error; repeat the same call with it to complete the destructive action it was issued for. Omit on the first call. | |
| no_paid | boolean | no | Refuse paid media generation for this run. Text and LLM work still bills normally. |
| max_paid_operations | integer | no | Maximum paid media reservations across all workspaces in this authenticated user/run, enforced atomically. Retries reuse their reservation. |
| spending_run_id | string | no | Stable run or conversation identity required with spending controls. The authenticated run owner shares one policy across workspaces. |
READ-ONLY. Live per-request JSON Schema forms: domain=contracts view=form target=<tool>[.<branch>] or a published output kind (StoryboardV1 aliases BuildPlanV1), agent_id required. Forms use the accepted tool contract and live choices. Versioned stage/job/delivery schemas: domain=contracts view=schemas (optional target model name). NEVER call this before an action and never to look up a target, pl
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | no | The agent ID (envelope; forwarded to every view that scopes by agent). Optional: only the agent-scoped views require it — the vidsheet/media engine views resolve the owning agent from the sheet's engi | |
| domain | string | no | Discovery domain: contracts | vidsheet | agent | asset | billing | content | generate | location | media | platform | publish | task | voice | watchlist | social | analyze | ask (views per domain in t |
| view | string | no | Pick by the user's question: 'what did my watchlist say/find/summarize' = gen_watchlist_action query_watchlist, never a watchlist view here; 'who can see/access X' (even about a sheet) = platform orga |
| vidsheet_id | no | Vidsheet ID | |
| row_id | no | Row ID (row, video, final_video_probe views) | |
| cell_id | no | Cell ID (cell, layers, layer, layer_analysis views; optional on layer — the owning cell is resolved from the layer id; on layer_analysis a cell_id without a layer_id addresses an ingredient media cell | |
| layer_id | no | Layer ID (layer, layer_analysis views; a layer id is unique on the sheet, so it is enough — pass cell_id to pin the read to one cell) | |
| template | no | Template slug/UUID/ID (template view) | |
| page | no | Page number (templates, sound_library, billing.usage and analyze.job rows views); an integer or a string of digits | |
| query | no | Search text (templates, sound_library, platform.conversations views; omit on sound_library to browse; conversations matches titles, max 200 characters) | |
| limit | no | Max rows in the selected view: change sets (operations, 1-100), conversations/messages (platform), or recommended sounds (media.recommended_sounds, 1-20, default 10) | |
| include_undone | no | Include undone change sets (operations view) | |
| commercial | no | Only sounds cleared for commercial use (sound_library and recommended_sounds views) | |
| mood | no | Mood filter (media sound_library and recommended_sounds views) | |
| tags | no | Tag filter (media sound_library view) | |
| genre | no | Genre filter (media recommended_sounds view) | |
| min_bpm | no | Minimum tempo in BPM (media recommended_sounds view) | |
| max_bpm | no | Maximum tempo in BPM (media recommended_sounds view) | |
| per_page | no | Results per page (sound_library view, default 10) | |
| include | no | Extra sections; ["full"] dumps the whole sheet on the sheet view |
Send feedback about GEN (a bug, an idea, praise) from the user to the GEN team. Call it whenever the user wants to report a problem, complain, suggest something or say thanks. Pass the user's words verbatim in message. The agent, the recent GEN calls of this session and the client are attached automatically; never ask the user for them. Always relay the returned thank-you to the user.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| message | string | yes | The user's feedback, in their own words. |
| category | no | What kind of feedback this is. Defaults to other. | |
| rating | no | An optional satisfaction rating from 1 to 5. | |
| agent_id | no | The agent this feedback is about, when the user names one. | |
| conversation_id | no | The conversation the feedback came from, when the client knows it. |
Create media with GEN: generate an image (create_image), a video clip (create_video), an original song (create_song), a DJ-style song mix (create_song_mix), or transcribe audio or video into text (transcribe). One call carries one or more typed actions. Paid generations spend credits and each result carries generation_id, user_job_id and estimated_credits — poll the gen_discover generation view wi
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | no | The agent ID that owns the workspace (envelope; routed per branch) | |
| actions | array | yes | One or more typed media actions: create_image (prompt, optional version/aspect_ratio/number_of_images/reference_images/content_resource_ids) | create_video (prompt, optional model/aspect_ratio/resolut |
| confirm_token | no | Single-use token from a CONFIRMATION_REQUIRED error; repeat the same call with it to complete the destructive action it was issued for. Omit on the first call. | |
| no_paid | boolean | no | Refuse paid media generation for this run. Text and LLM work still bills normally. |
| max_paid_operations | integer | no | Maximum paid media reservations across all workspaces in this authenticated user/run, enforced atomically. Retries reuse their reservation. |
| spending_run_id | string | no | Stable run or conversation identity required with spending controls. The authenticated run owner shares one policy across workspaces. |
Compose the weekly We Believe report's source-grounded ideas through the one billed content-ideas generator (the same path gen_content_action generate_ideas uses; this tool never calls a model directly). The caller injects the master playbook text, the measured comments and the verified first-party reference corpus with explicit freshness. The playbook text, the selected comment and the relevant v
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | string | yes | The agent ID the report ideas belong to (envelope; the generation is billed to it) |
| sources | array | yes | Measured Instagram/TikTok comments; each carries its stable source_key, platform, url, text, likes, published_at, aliases and the master-playbook principle it serves |
| references | array | yes | Verified first-party We Believe references (official site or @webelieveinedu) with explicit observed_at; each declares the playbook principles it supports |
| playbook_principles | array | yes | The current master playbook's closed principle names |
| playbook_text | string | yes | The current master playbook's own mission/voice text; every playbook principle must appear in it, and it grounds the idea generator as We Believe |
| count | integer | yes | How many report ideas to compose (at most one per selected comment) |
| report_key | string | yes | Stable report run key; one idempotency key per source is derived from it so a retry cannot start a second billed run |
| period_end | no | Window end instant (ISO 8601 UTC); defaults to now | |
| excluded_keys | no | Source keys/aliases already used in earlier reports | |
| peer_evidence | no | Verified peer posts with exact metrics; passed to the generator as evidence and attached verbatim, never inferred or topped up |
Workspace and access admin for an agent: create, rename, or delete an organization (create_organization, update_organization, delete_organization), upgrade its workspace plan (upgrade_workspace), manage its Personal Access Tokens (create_api_key, update_api_key, revoke_api_key, revoke_all_api_keys), set per-conversation session preferences (update_session_preferences), and back up GEN assets to Wa
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | no | The agent ID that owns the workspace (envelope; routed into the backup branches) | |
| actions | array | yes | One or more typed platform actions: create_api_key (optional name/expires_in) | create_organization (name) | create_proof_of_genesis_backup (asset_url, optional asset_type/visibility/encrypted/encrypt |
| confirm_token | no | Single-use token from a CONFIRMATION_REQUIRED error; repeat the same call with it to complete the destructive action it was issued for. Omit on the first call. |
Step 5 (Export & Publish): Ship posts to social platforms — schedule, publish, update, or remove posts. One call carries one or more typed actions: schedule_post_<platform> (media_url and that platform's fields; schedule_type 'now' or 'specific_time' with scheduled_time; a field of another platform is rejected) | publish_content (platform + media_url + description + schedule_type) | update_schedul
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | no | The agent ID that owns the connected accounts (envelope; routed per branch) | |
| actions | array | yes | One or more typed publish actions: schedule_post_tiktok (media_url, tiktok_privacy_level, tiktok_disable_comment, tiktok_disable_duet, tiktok_disable_stitch, optional description/thumbnail_url/tiktok_ |
| confirm_token | no | Single-use token from a CONFIRMATION_REQUIRED error; repeat the same call with it to complete the destructive action it was issued for. Omit on the first call. |
Create a one-time GEN sign-in link for the caller's own account so its owner can open GEN in a browser. Requires the self-serve account owner's agent PAT. Use it when the user asks to sign in to GEN, open GEN, or get into the agent-created account from this client. For a plan or credit-pack checkout, use gen_billing_action open_checkout instead; Stripe needs no GEN browser sign-in. Pass the GEN UR
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | The GEN URL the signed-in browser should land on, e.g. https://gen.pro/projects/123?view=editor#clip |
Run the task control plane: create, update, pause, resume, delete, duplicate, and run-now recurring jobs ('daily tasks' — a schedule plus a saved prompt), manage content-monitoring jobs, and approve or reject a gated agent run (decide_agent_run). One call carries one or more typed actions. pause_recurring_job/resume_recurring_job/delete_recurring_job act on the named job (update_recurring_job too)
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | no | The agent ID that owns the jobs (envelope; routed per branch) | |
| actions | array | yes | One or more typed task actions (agent_id rides the envelope, never inside entries): create_recurring_job (job_type, prompt, optional name/schedule/delivery/next_run_at) | ensure_default_recurring_job |
| confirm_token | no | Single-use token from a CONFIRMATION_REQUIRED error; repeat the same call with it to complete the destructive action it was issued for. Omit on the first call. |
Upload a file into an agent's owned asset library without sending the bytes through the MCP call. One tool, three phases. phase=request_upload (default) takes agent_id, filename and content_type and returns upload_id, a same-origin signed PUT URL, a ready-to-run curl command and a browser drop_url; the signed capability expires in about 5 minutes and is single use. phase=create_drop returns the sa
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | no | The agent that will own the uploaded asset (required for request_upload, create_drop and a host file reference) | |
| phase | string | no | request_upload: mint a signed PUT URL and curl. create_drop: the same, framed for a browser drop page. status: read the owned asset for an upload_id. |
| filename | no | Original filename including extension (request_upload/create_drop); its extension must match content_type | |
| content_type | no | MIME type of the file (e.g. image/jpeg, audio/mpeg, video/mp4, application/pdf) | |
| upload_id | no | The upload_id returned by request_upload/create_drop (status only) | |
| file | no | A host-provided file reference {download_url, file_id, optional mime_type/file_name}, or the host's placeholder string. The server fetches download_url; never a local path. | |
| folder_id | no | Place the completed asset inside this asset folder |
Vidsheet: skill://gen/vidsheet-mcp/SKILL.md; host-approved resources/read or prompt vidsheet-mcp. Step 4 (Edit & Generate): the Vidsheet write tool for the editable video workspace. A direct saved idea draft/full uses gen_content_action action=create_video_from_idea; a separately authored scene-form storyboard uses apply_storyboard on one owned row. Generic create_sheet/actions[] create must not r
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | no | The agent that owns the vidsheet. Optional when the call names the sheet (vidsheet_id): the owner resolves from the engine read. Required for create_sheet/clone_template/create_engine and a call namin | |
| op | no | The write op (named in the tool description). Omit when sending the canonical 'actions' envelope. | |
| actions | no | Canonical Rails action envelope: a non-empty list of {"action", "target", "values"|"ids"} objects, relayed to Rails verbatim (GEN-6700); pass either this or a flat op, never both. A row's output video | |
| source_inputs | no | Resolved saved input media for the envelope's per-action source references (MCP-only; never relayed to Rails): {attachments: [{ref, url, kind, content_resource_id, resource...}]}. Each reference binds | |
| bindings | no | Saved-input bindings for this envelope (MCP-only; never relayed to Rails): one {index, references} per action, where index names that action and references is [{input_id, card_type?, field?}]. The MCP | |
| vidsheet_id | no | Vidsheet ID (every op except create_sheet/clone_template/create_engine) | |
| generation_id | no | Generation ID (continue_generation, stop_generation, refund_unused_output) | |
| build_run_id | no | Errored build run identity (refund_unused_output); relayed to Rails as audit metadata | |
| reason | no | Reason the output was unused (refund_unused_output); relayed to Rails unchanged | |
| content_resource_id | no | Owned video asset ID to analyze (generate source_video_analysis) | |
| mode | no | Analysis mode, default recreate (generate source_video_analysis) | |
| cell_id | no | Cell ID (set_cell, layers, card owner/target); a global's value_cell_id addresses its value cell | |
| row_id | no | Source row for generate sound_matching | |
| row_position | no | apply_storyboard only: one-based displayed row position on the owned Vidsheet, instead of row_id | |
| variable_id | no | Global-variable row id from gen_discover view=variables, never the value cell id: generate resolves it to that value cell as the owner (instead of cell_id/layer_id) | |
| layer_id | no | Layer ID (update_layer, generate layer, card owner/target) | |
| layer_row | no | Timeline row/track for add_layer and update_layer, 0-based (settings.row); layers sharing a row play sequentially. One of the ten tracks 0..9 | |
| name | no | Sheet name (create_sheet; duplicate_sheet renames the copy) | |
| blank | no | Set true when the user asks for an empty or blank sheet, or names only the columns they want. Skips the onboarding template and default columns/rows; omitted or false preserves default creation. Canno | |
| template_slug | no | Template slug (optional on create_sheet; clone_template; create_engine requires it with idea_id); discover valid choices with gen_discover vidsheet view=templates |
Build a custom voice for an agent: clone one from an audio sample (clone_voice), design one from a scripted prompt flow (generate_voice_script, generate_voice_description, generate_voice_samples, design_voice), audition one with a spoken preview (preview_voice), or remove one you own (delete_voice). One call carries one or more typed actions. Deleting a voice is permanent — confirm which voice fir
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | no | The agent ID that owns the voices (envelope; routed into every branch) | |
| actions | array | yes | One or more typed voice actions: clone_voice (name, optional audio_url/audio_base64/gender/language/description) | design_voice (generation_id, name, REQUIRED sample audio: audio_base64 (the Rails bas |
| confirm_token | no | Single-use token from a CONFIRMATION_REQUIRED error; repeat the same call with it to complete the destructive action it was issued for. Omit on the first call. |
Run one or more watchlist operations in a single call: create, update, pause, resume or delete a watchlist, add or remove a monitoring source, or ask a question about a watchlist (query_watchlist starts an agent run and returns a run_id to poll). One call carries one or more typed actions. Deleting a watchlist or removing a source is destructive — confirm with the user first. delete_watchlist is t
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | no | The agent ID that owns the watchlists (envelope; routed per branch) | |
| actions | array | yes | One or more typed watchlist actions: create_watchlist (name, optional sources/project_id/conversation_id/created_by_run_id) | update_watchlist (watchlist_id or watchlist_name, optional name/project_id |
| confirm_token | no | Single-use token from a CONFIRMATION_REQUIRED error; repeat the same call with it to complete the destructive action it was issued for. Omit on the first call. |
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
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install GEN or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 90 / 100
Release 0.2.2 · scanned 22 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 score90
Findings0 threat · 8 capability
Capabilityhigh
Coveragemanifest
Verificationnot in this report
Surface digest076b33a4b10c02be43be2c563703867aefa79440044ae6cb22a3660ccdf83087
Score vectorthreat 100 → client 90
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| 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. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| gen_agent_action | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| gen_analyze | untrusted-inputexternal-sink | untrusted-input: keyword "fetch"; external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| gen_ask | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| gen_asset_action | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| gen_billing_action | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| gen_characters | code-execexternal-sink | code-exec: parameter "script"; external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| gen_content_action | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| gen_discover | untrusted-input | untrusted-input: keyword "scrape", declares openWorldHint: true (interacts with entities outside the server) |
| gen_feedback | state-write | state-write: declares readOnlyHint: false |
| gen_generate | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| gen_generate_report_ideas | state-write | state-write: declares readOnlyHint: false |
| gen_platform_action | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| gen_publish_action | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| gen_sign_in_link | state-write | state-write: declares readOnlyHint: false |
| gen_task_action | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| gen_upload_asset | untrusted-inputexternal-sinkstate-write | untrusted-input: keyword "download"; external-sink: keyword "curl"; state-write: declares readOnlyHint: false |
| gen_vidsheet_action | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| gen_voice_action | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| gen_watchlist_action | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
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 digest076b33a4b10c02be
Scanned2026-10-22
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.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 0.2.2.
0.2.2
undated
latest- The version the registry reports for this listing; it was 0.2.1.
0.2.1
undated
- The version the registry reports for this listing; it was 0.1.29.
0.1.29
12 Aug 2026
No release note was published with this version.
0.1.10
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish GEN can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.