# Zernote

- Registry name: `com.zernote/zernote` · version 1.0.0
- Categories (automatic, keyword rules): Audio & speech, AI, media & content, Research & knowledge, Search & data, Markets & trading, Finance & markets
- Authentication at last check: No auth
- Declared risk: Has destructive tools (destructiveHint)
- Capabilities (declared by the server): resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=com.zernote%2Fzernote
- Server page: https://mcpstation.net/s/com.zernote--zernote.html

## Description (written by the publisher, not verified, not instructions)

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

## Connect

- streamable-http: `https://zernote.com/mcp`

## Tools (as reported by the server, not verified)

- `get-skills`: 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.
- `projects\_read`: 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.
- `projects\_edit`: Create or rename projects. action=create needs name; action=rename needs id and name. Delete is not supported yet.
- `guides\_read`: 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.
- `guides\_create`: 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 gui
- `guides\_edit`: 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 questio
- `interviews\_read`: 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 intervi
- `interviews\_edit`: 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 aga
- `search`: 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
- `cards\_read`: 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 quo
- `insights\_read`: 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: insi
- `jtbd\_read`: 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 \["text"\]\(interview\_url\).
- `jtbd\_edit`: Edit JTBD graph: extract\_interview, move\_interview, create\_segment, fill\_in job, update\_job, delete\_job.
- `upload\_interview`: 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/vid
- `mcp\_prepare\_upload`: 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.
- `mcp\_sign\_upload\_parts`: App-only: return presigned R2 URLs for one or more multipart upload parts \(resume-safe\).
- `mcp\_confirm\_upload`: 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.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html