Name: Zernote
Author: zernote

Zernote MCP

User research workspace to transcribe interviews and turn conversations into insights.

Tool-list grade A Remote · Streamable HTTP No auth needed 17 tools v1.0.0

No reviews yet by zernote 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

User research workspace to transcribe interviews and turn conversations into insights.

Quickstart

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

# 2 — ask your agent for something these tools do
#   get-skills, projects_read, projects_edit and 14 more

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

Publishernot claimed

zernote1 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

Use for startup ideas, office hours, and “I installed this connector to work through an idea”. Inside: office-hours-zernote (challenge the idea), zernote-plan-research. Omit id for the catalog, then pass id for the full playbook. Not for listing interviews or projects. Works without login.

Parameter	Type	Required	Notes
id	string	no	Skill id. Empty = catalog. Examples: office-hours-zernote, zernote-plan-research.

Read existing research folders. Not for a new startup idea or office hours — call get-skills first. action=list returns projects for the authenticated user.

Parameter	Type	Required	Notes
action	string	yes	Read action. Currently only list.
limit	integer	no	Max number of projects to return (default 50, max 200).
offset	integer	no	Number of projects to skip before returning results (default 0).

Create or rename projects. action=create needs name; action=rename needs id and name. Delete is not supported yet.

Parameter	Type	Required	Notes
action	string	yes	Edit action.
description	string	no	Optional project description (create/rename).
id	string	no	Project UUID (required for rename).
name	string	no	Project name (required for create and rename).

Read the interview guide stored on a project. The guide has an intro, ordered blocks (title, minutes, questions, notes), total time, a notes template, and any markdown that did not parse. Returns an empty guide when the project has none.

Parameter	Type	Required	Notes
project_id	string	yes	Project UUID.

Create the first interview guide on a project. Use this to upload a new guide. Pass structured fields, not markdown: intro, blocks (title, minutes, notes, questions with text/note/key), and notes_template. Needs at least one block with a title. Fails if the project already has a guide — then use guides_edit. Core does not show the guide. Live reads it on the project.

Parameter	Type	Required	Notes
blocks	array	yes	Timed sections in interview order.
intro	string	no	Spoken opening before the first block.
notes_template	string	no	Post-interview notes template (conspect).
project_id	string	yes	Project UUID.

Replace an existing interview guide from markdown. To create the first guide, call guides_create. Text before the first ## is the intro. ## Title (12) or ## Title (7–11) is a block; minutes are the last number in parentheses. Lines starting with - or 1. are questions; a leading * marks a key question; the next indented line is the question note. A paragraph under the block heading before the first

Parameter	Type	Required	Notes
markdown	string	yes	Full guide markdown. Replaces the guide stored on the project.
project_id	string	yes	Project UUID.

Read interviews. Typical path: (1) action=list with summary_mode=brief (default) — returns the short # Summary. List items include need_approve_speakers (+ pending_speakers / hint): when true, show interviewer quote links then confirm via assign_speakers; one identity confirm backfills other interviews sharing voice_identity_id. Use summary_mode=brief for renaming or folder triage. Use summary_mod

Parameter	Type	Required	Notes
action	string	yes	Read action. Use list (brief or summary_mode=full) for overview; use transcript when you need a quote window.
around_chunk_index	integer	no	Transcript only: expand a window around this vector-search chunk_index (use instead of blind offset when available).
folder_id	string	no	Deprecated alias for project_id.
id	string	no	Interview UUID (required for get, status, transcript).
inbox_only	boolean	no	When true with action=list, list Inbox interviews (no project). Ignored if project_id is set.
limit	integer	no	For list: max interviews (default 20, max 100). For transcript: max characters (default 4000, max 20000).
notes_mode	string	no	List only. none (default) = omit notes body. full = researcher notes (truncated on list). Use summary when notes are not required.
offset	integer	no	For list: skip count. For transcript without around_chunk_index: character offset (default 0).
project_id	string	no	Optional project UUID to filter list (alias: folder_id).
radius_chars	integer	no	Transcript only with around_chunk_index: chars before/after chunk match (default 1500, max 8000).
summary_mode	string	no	List only. brief (default) = short # Summary for triage/rename. full = all summary_fragments (profile/tools/pains/other_topics) when brief is insufficient.

Rename, move, write summary/notes, retranscribe, assign/confirm speakers, or toggle voiceprint. action=rename needs id+title; move needs interview_ids (+ optional project_id); write_summary needs id+summary; write_notes needs id+notes; retranscribe needs id+language (charges transcription tokens again; analyze-only, keeps notes). assign_speakers needs id+speaker_labels+assigned_names. For voicepri

Parameter	Type	Required	Notes
action	string	yes	Edit action.
assigned_names	array	no	Human names matching speaker_labels (assign_speakers). Use a real name, not "Interviewer N".
enabled	boolean	no	Voiceprint on/off (set_voiceprint). false deletes stored voice biometrics.
folder_id	string	no	Deprecated alias for project_id.
id	string	no	Interview UUID (rename, write_summary, write_notes, retranscribe, assign_speakers).
interview_ids	array	no	Interview UUIDs to move.
language	string	no	Transcription language code for retranscribe (e.g. en, ru, nl). Charges tokens for audio duration.
notes	string	no	Full note text that replaces the existing notes field (write_notes).
project_id	string	no	Destination project UUID for move (alias: folder_id). Omit or null for Inbox.
speaker_labels	array	no	Diarization labels to assign (assign_speakers), e.g. ["A"]. Voiceprint interviewer confirm: one label in this call (same identity then backfills other interviews).
summary	string	no	Full summary markdown that replaces the existing summary (write_summary). Expected sections: # Summary, ## Profile, ## Tools & workflow, ## Pains & friction, # Other topics.
title	string	no	New title (rename).

Semantic search for evidence / counter-evidence after you have interview context (e.g. from list/summary). Optional interview_id scopes search to one interview and returns smaller text windows. Returns matching_chunks[{chunk_index, text, similarity, start_seconds?, url}]. CITATION REQUIRED: actively cite hits to the user as markdown ["verbatim quote from text"]({base_url}/project/interview/{id}?t=

Parameter	Type	Required	Notes
chunks_limit	integer	no	Max matching chunks per interview (default 3 corpus / 8 when interview_id set; max 10 / 20).
chunks_offset	integer	no	Skip this many top chunks per interview (default 0).
interview_id	string	no	Optional interview UUID — search only inside this interview; returns smaller chunk windows.
limit	integer	no	Max number of interviews to return (default 5, max 10). Ignored when interview_id is set.
query	string	yes	Natural language search query (hypothesis / claim to evidence).

List L2 coded claim-cards (claim + optional quote + chunk_index + lens + codes + start_seconds? + url). Filter by project_id, interview_id / interview_ids, codes (any match), or lens (workflow|gtm|privacy|other). CITATION REQUIRED: actively cite each card.quote to the user as markdown ["verbatim quote"]({base_url}/project/interview/{id}?t={seconds}) using item.url from the tool result (already abs

Parameter	Type	Required	Notes
codes	array	no	Optional code tags; any match (e.g. pain:synthesis, gtm:pricing).
folder_id	string	no	Deprecated alias for project_id.
interview_id	string	no	Optional interview UUID to scope cards.
interview_ids	array	no	Optional interview UUIDs to scope cards.
lens	string	no	Optional exact lens filter.
limit	integer	no	Max cards to return (default 50, max 200).
offset	integer	no	Number of cards to skip (default 0).
project_id	string	no	Optional project UUID — cards from interviews in this project (alias: folder_id).

Read the project Insights graph in pages or by node. action=list returns a compact folder-wide outline (groups + interviews) plus a page of insight bodies. Filter with interview_id, group_id (DB UUID, not UI group-0), group_name, insight_ids, or ungrouped_only. action=get_node returns one node: insight | interview | group | ungrouped. CITATION REQUIRED: actively cite each item.quote as markdown ["

Parameter	Type	Required	Notes
action	string	yes	list = paged insight bodies + outline. get_node = one insight, interview, group, or ungrouped cluster.
folder_id	string	no	Deprecated alias for project_id.
group_id	string	no	List filter: insight_groups.id UUID (not a render index like group-0).
group_name	string	no	List filter: case-insensitive group name match.
id	string	no	get_node: insight, interview, or group UUID. Not used for ungrouped.
insight_ids	array	no	List filter: only these insight UUIDs.
interview_id	string	no	List filter: only insights from this interview. Interview must be in the project.
limit	integer	no	List only: max insight bodies (default 25, max 100).
node_type	string	no	get_node: which node to load.
offset	integer	no	List only: skip this many matching insight bodies (default 0).
project_id	string	no	Project/folder UUID (required for list and for get_node group/ungrouped/insight).
ungrouped_only	boolean	no	List filter: only insights that are not in a cross-interview group.

Read JTBD job graph segments and trees. action=list_segments needs folder_id/project_id. action=get_tree needs segment_id or interview_id. CITATION REQUIRED: cite job quotes as ["text"](interview_url).

Parameter	Type	Required	Notes
action	string	yes	—
folder_id	string	no	Project/folder UUID (list_segments).
interview_id	string	no	Interview UUID (get_tree).
project_id	string	no	Alias for folder_id.
segment_id	string	no	Segment UUID (get_tree).

Edit JTBD graph: extract_interview, move_interview, create_segment, fill_in job, update_job, delete_job.

Parameter	Type	Required	Notes
action	string	yes	—
category	string	no	—
folder_id	string	no	—
human_edited	boolean	no	—
i_want_to	string	no	—
interview_id	string	no	—
job_id	string	no	—
language	string	no	Job tree language for extract_interview (en or ru). Defaults to en. Quotes stay in the interview language.
name	string	no	—
project_id	string	no	—
segment_id	string	no	—
so_that	string	no	—
to_segment_id	string	no	—
when	string	no	—

Opens the in-Claude MCP Apps widget "Upload To Zernote" so the user can drop a file into Inbox in this chat (audio/video max 2GB; text .txt/.md or PDF max 50MB). Use when the user wants to upload/add an interview or get started on an empty account — this is the usual ingest path in Claude. Audio/video starts transcription; text/PDF become ready immediately (no speaker diarization). Claude can name

No parameter schema on file.

App-only: create an Inbox interview and return a presigned R2 upload URL (or multipart upload_id for large files). Pass interview_id (+ upload_id for multipart) to resume without a new card.

Parameter	Type	Required	Notes
content_type	string	no	MIME type for the PUT (optional).
filename	string	yes	Original filename.
interview_id	string	no	Optional: existing empty interview UUID — resume upload without creating a new card.
size_bytes	integer	yes	File size in bytes.
title	string	no	Optional interview title (defaults to sanitized filename).
upload_id	string	no	Optional multipart upload id from a previous prepare (resume).

App-only: return presigned R2 URLs for one or more multipart upload parts (resume-safe).

Parameter	Type	Required	Notes
interview_id	string	yes	Interview UUID from prepare.
object_key	string	yes	R2 object key from prepare.
part_numbers	array	yes	Part numbers to sign (1-based, max 20).
upload_id	string	yes	Multipart upload id from prepare.

App-only: confirm a completed R2 upload (single PUT or multipart) for an Inbox interview. Audio/video is enqueued for transcription (STT + diarization). Text (.txt/.md) and PDF are stored and marked ready immediately — no transcription.

Parameter	Type	Required	Notes
filename	string	yes	Original filename.
interview_id	string	yes	Interview UUID from prepare.
language	string	yes	STT language for audio/video (e.g. en, ru, nl). Not used for text/PDF (no transcription).
multipart_parts	array	no	Completed parts (part_number + etag) when using multipart.
multipart_upload_id	string	no	Multipart upload id — complete assembly before confirm.
object_key	string	yes	R2 object key from prepare.
size_bytes	integer	yes	File size in bytes.
title	string	no	Optional title to apply before confirm.

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 Zernote or to call it, at any volume.

ATool-list grade · score 93 / 100

Release 1.0.0 · 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 · 0 capability

Capabilitymoderate

Coveragemanifest

Verificationnot in this report

Surface digest5f6a08572e70152e5065d34a4a139d146bbea390db68fe46272272aae0a115f9

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
get-skills	no tags
projects_read	no tags
projects_edit	state-write	state-write: declares readOnlyHint: false
guides_read	no tags
guides_create	state-write	state-write: declares readOnlyHint: false
guides_edit	state-write	state-write: declares readOnlyHint: false, destructiveHint: true
interviews_read	no tags
interviews_edit	state-write	state-write: declares readOnlyHint: false, destructiveHint: true
search	no tags
cards_read	no tags
insights_read	no tags
jtbd_read	no tags
jtbd_edit	state-write	state-write: declares readOnlyHint: false, destructiveHint: true
upload_interview	state-write	state-write: declares readOnlyHint: false
mcp_prepare_upload	state-write	state-write: declares readOnlyHint: false
mcp_sign_upload_parts	state-write	state-write: declares readOnlyHint: false
mcp_confirm_upload	state-write	state-write: declares readOnlyHint: false

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.

The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.

Supply chain and provenance

Integrityfirst-seen

Surface digest5f6a08572e70152e

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

Zernote 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