Zernote

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

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

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Zernote": {
      "url": "https://zernote.com/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (17)

• get-skills read-only

  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.

  Parameters:

  • id — string — Skill id. Empty = catalog. Examples: office-hours-zernote, zernote-plan-research.

  Hints: read-only yes · destructive no · idempotent not declared · open-world not declared

• projects_read read-only

  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.

  Parameters:

  • action (required) — string — Read action. Currently only list.
  • limit — integer — Max number of projects to return (default 50, max 200).
  • offset — integer — Number of projects to skip before returning results (default 0).

  Hints: read-only yes · destructive no · idempotent not declared · open-world not declared

• projects_edit

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

  Parameters:

  • action (required) — string — Edit action.
  • id — string — Project UUID (required for rename).
  • name — string — Project name (required for create and rename).
  • description — string — Optional project description (create/rename).

  Hints: read-only no · destructive no · idempotent not declared · open-world not declared

• guides_read read-only

  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.

  Parameters:

  • project_id (required) — string — Project UUID.

  Hints: read-only yes · destructive no · idempotent not declared · open-world not declared

• 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 guides_edit. Core does not show the guide. Live reads it on the project.

  Parameters:

  • project_id (required) — string — Project UUID.
  • blocks (required) — array — Timed sections in interview order.
  • intro — string — Spoken opening before the first block.
  • notes_template — string — Post-interview notes template (conspect).

  Hints: read-only no · destructive no · idempotent not declared · open-world not declared

• guides_edit destructive

  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 question is the block note. ## Конспект is the post-interview notes template, not a block. Optional line `Общее время: 30` or `Total: 30` sets total minutes; otherwise they are the sum of block minutes. Anything that does not match is returned in remainder and kept, not dropped. The previous guide is replaced entirely.

  Parameters:

  • project_id (required) — string — Project UUID.
  • markdown (required) — string — Full guide markdown. Replaces the guide stored on the project.

  Hints: read-only no · destructive yes · idempotent not declared · open-world not declared

• interviews_read read-only

  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_mode=full when Profile/Tools/Pains/Other topics are needed for deeper analysis. (2) call `search` when you need evidence or counter-evidence for a hypothesis; (3) use action=transcript with around_chunk_index from matching_chunks when a quote window is required. CITATION REQUIRED: when answering the user, actively cite evidence as markdown ["verbatim quote"]({base_url}/project/interview/{id}?t={seconds}) using interview_url / matching chunk url from tool results (includes ?t= when start_seconds is set). Prefer quotes over paraphrase.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent not declared · open-world not declared

• interviews_edit destructive

  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 voiceprint interviewer confirm: one label + real name on one interview after quote links; that identity backfills other interviews sharing voice_identity_id — re-list instead of confirming every card. set_voiceprint needs enabled bool (false purges biometric voice data). If need_approve_speakers=true, show quote links then assign_speakers when the user confirms. If transcript_quality.looks_corrupted=true, offer retranscribe with the correct language. write_notes and write_summary replace the entire notes or summary field (not append).

  Parameters:

  • action (required) — string — Edit action.
  • id — string — Interview UUID (rename, write_summary, write_notes, retranscribe, assign_speakers).
  • notes — string — Full note text that replaces the existing notes field (write_notes).
  • title — string — New title (rename).
  • enabled — boolean — Voiceprint on/off (set_voiceprint). false deletes stored voice biometrics.
  • summary — string — Full summary markdown that replaces the existing summary (write_summary). Expected sections: # Summary, ## Profile, ## Tools & workflow, ## Pains & friction, # Other topics.
  • language — string — Transcription language code for retranscribe (e.g. en, ru, nl). Charges tokens for audio duration.
  • folder_id — string — Deprecated alias for project_id.
  • project_id — string — Destination project UUID for move (alias: folder_id). Omit or null for Inbox.
  • interview_ids — array — Interview UUIDs to move.
  • assigned_names — array — Human names matching speaker_labels (assign_speakers). Use a real name, not "Interviewer N".
  • speaker_labels — array — Diarization labels to assign (assign_speakers), e.g. ["A"]. Voiceprint interviewer confirm: one label in this call (same identity then backfills other interviews).

  Hints: read-only no · destructive yes · idempotent not declared · open-world not declared

• search read-only

  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={seconds}) using each chunk's url field from the tool result (already absolute; includes ?t= when start_seconds is present). Prefer quoting matching_chunks over paraphrase. Expand with interviews_read action=transcript around_chunk_index when a wider quote window is needed.

  Parameters:

  • query (required) — string — Natural language search query (hypothesis / claim to evidence).
  • limit — integer — Max number of interviews to return (default 5, max 10). Ignored when interview_id is set.
  • chunks_limit — integer — Max matching chunks per interview (default 3 corpus / 8 when interview_id set; max 10 / 20).
  • interview_id — string — Optional interview UUID — search only inside this interview; returns smaller chunk windows.
  • chunks_offset — integer — Skip this many top chunks per interview (default 0).

  Hints: read-only yes · destructive no · idempotent not declared · open-world not declared

• cards_read read-only

  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 absolute; includes ?t= when start_seconds is set). Prefer quotes over paraphrase. Verify with interviews_read action=transcript around_chunk_index when a wider quote window is needed.

  Parameters:

  • lens — string — Optional exact lens filter.
  • codes — array — Optional code tags; any match (e.g. pain:synthesis, gtm:pricing).
  • limit — integer — Max cards to return (default 50, max 200).
  • offset — integer — Number of cards to skip (default 0).
  • folder_id — string — Deprecated alias for project_id.
  • project_id — string — Optional project UUID — cards from interviews in this project (alias: folder_id).
  • interview_id — string — Optional interview UUID to scope cards.
  • interview_ids — array — Optional interview UUIDs to scope cards.

  Hints: read-only yes · destructive no · idempotent not declared · open-world not declared

• insights_read read-only

  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 ["verbatim quote"]({base_url}/project/interview/{id}?t={seconds}) using item.url from the tool result (already absolute; includes ?t= when start_seconds is set). Prefer quotes over paraphrase. Do not use quote_start — that is a character offset, not a player timestamp.

  Parameters:

  • action (required) — string — list = paged insight bodies + outline. get_node = one insight, interview, group, or ungrouped cluster.
  • id — string — get_node: insight, interview, or group UUID. Not used for ungrouped.
  • limit — integer — List only: max insight bodies (default 25, max 100).
  • offset — integer — List only: skip this many matching insight bodies (default 0).
  • group_id — string — List filter: insight_groups.id UUID (not a render index like group-0).
  • folder_id — string — Deprecated alias for project_id.
  • node_type — string — get_node: which node to load.
  • group_name — string — List filter: case-insensitive group name match.
  • project_id — string — Project/folder UUID (required for list and for get_node group/ungrouped/insight).
  • insight_ids — array — List filter: only these insight UUIDs.
  • interview_id — string — List filter: only insights from this interview. Interview must be in the project.
  • ungrouped_only — boolean — List filter: only insights that are not in a cross-interview group.

  Hints: read-only yes · destructive no · idempotent not declared · open-world not declared

• jtbd_read read-only

  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).

  Parameters:

  • action (required) — string
  • folder_id — string — Project/folder UUID (list_segments).
  • project_id — string — Alias for folder_id.
  • segment_id — string — Segment UUID (get_tree).
  • interview_id — string — Interview UUID (get_tree).

  Hints: read-only yes · destructive no · idempotent not declared · open-world not declared

• jtbd_edit destructive

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

  Parameters:

  • action (required) — string
  • name — string
  • when — string
  • job_id — string
  • so_that — string
  • category — string
  • language — string — Job tree language for extract_interview (en or ru). Defaults to en. Quotes stay in the interview language.
  • folder_id — string
  • i_want_to — string
  • project_id — string
  • segment_id — string
  • human_edited — boolean
  • interview_id — string
  • to_segment_id — string

  Hints: read-only no · destructive yes · idempotent not declared · open-world not declared

• 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/video starts transcription; text/PDF become ready immediately (no speaker diarization). Claude can name interviews after upload.

  Hints: read-only no · destructive no · idempotent not declared · open-world not declared

• 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.

  Parameters:

  • filename (required) — string — Original filename.
  • size_bytes (required) — integer — File size in bytes.
  • title — string — Optional interview title (defaults to sanitized filename).
  • upload_id — string — Optional multipart upload id from a previous prepare (resume).
  • content_type — string — MIME type for the PUT (optional).
  • interview_id — string — Optional: existing empty interview UUID — resume upload without creating a new card.

  Hints: read-only no · destructive no · idempotent not declared · open-world not declared

• mcp_sign_upload_parts

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

  Parameters:

  • interview_id (required) — string — Interview UUID from prepare.
  • object_key (required) — string — R2 object key from prepare.
  • upload_id (required) — string — Multipart upload id from prepare.
  • part_numbers (required) — array — Part numbers to sign (1-based, max 20).

  Hints: read-only no · destructive no · idempotent not declared · open-world not declared

• 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.

  Parameters:

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

  Hints: read-only no · destructive no · idempotent not declared · open-world not declared

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.