kedimeet-mcp
OfficialKediMeet MCP server
Ask Claude, Cursor, Codex or any other MCP client about your calls. This read-only server lets an AI assistant search and read the meetings that KediMeet recorded on your Mac: transcripts by speaker, and summaries with decisions, tasks and open questions.
You: What did Daniel promise me this week?
Claude: The screenshots for your onboarding copy, by Wednesday noon. He said it at 0:16 on Launch sync, Nov 18.
The assistant finds the right meeting itself, names it and its date, and gives the minute in the recording for quotes. More examples: kedimeet.app/ai.
Requirements
A Mac with KediMeet, free. The server reads the meetings folder KediMeet keeps on your Mac (
~/Library/Application Support/KediMeet). KediMeet doesn't need to be running.uv.
uvxdownloads Python and themcplibrary on first run.
Related MCP server: meetily-mcp
Connect
From KediMeet, no Terminal. Open Settings → Integrations and click Connect next to Claude, Claude Code, Cursor or Codex. KediMeet ships this server inside the app and writes the app's settings for you. Restart Claude or Cursor afterwards; Claude Code and Codex pick it up in a new session.
By hand, any MCP client (claude_desktop_config.json, ~/.cursor/mcp.json and the like):
{
"mcpServers": {
"kedimeet": {
"command": "uvx",
"args": ["kedimeet-mcp"]
}
}
}Apps opened from the Dock don't see your shell's PATH, so if the app can't start uvx, put its full path in
command (which uvx prints it).
Claude Code:
claude mcp add --scope user kedimeet -- uvx kedimeet-mcpCodex (~/.codex/config.toml):
[mcp_servers.kedimeet]
command = "uvx"
args = ["kedimeet-mcp"]
startup_timeout_sec = 60If you moved your meetings to another folder in KediMeet, add its path as the last argument:
uvx kedimeet-mcp "/Volumes/Archive/KediMeet".
Tools
Tool | What it does |
| Finds words in transcripts and summaries over a period, best matches first. Matches words with different endings. |
| Meetings in a period, newest first: title, date, participants, the main point of the summary. |
| The full summary: decisions, tasks with done marks, open questions, who spoke how much, the call link and your own notes. |
| The transcript turn by turn, |
All four are marked read-only (readOnlyHint). None of them writes, deletes or goes to the network.
Privacy
The server runs on your Mac over stdio and only reads files in the meetings folder. KediMeet's servers aren't involved. What the assistant reads becomes part of your conversation, and its provider (Anthropic, OpenAI and others) handles it under their own terms, as with anything you paste into a chat.
Development
uv run test_server.pyserver.py is the whole server. The KediMeet app ships the same file and runs it with uv run --script.
License
MIT, see LICENSE. The KediMeet name and the cat mascot are not covered, see NOTICE.
Available Tools
4 toolsget_meetingRead a meeting summaryARead-onlyIdempotent
The full summary of a meeting: the short version, decisions, tasks (marked done or not), open questions, participants and how much each of them spoke, the call link, and the notes the user wrote for the meeting. For "What are my action items from the Northwind call?", "Write a follow-up email after today's sync", "Which tasks from Monday are still open?" Read-only.
Inputs: meeting (required). Returns: result
get_transcriptRead a transcriptARead-onlyIdempotent
The transcript turn by turn: "[time] Name: text". For exact wording and context: "What exactly did Priya say about the deadline?", "Quote the client's objection". Read a long meeting (an hour is about 60,000 characters) in pieces around the place search pointed to. Read-only.
Inputs: meeting (required), end, start. Returns: result
list_meetingsList meetingsARead-onlyIdempotent
Meetings in a period, newest first: title, date, participants and the main point of the summary. For questions like "What calls did I have this week?", "Catch me up on yesterday's meetings", "When did I last talk to Daniel?" Read-only.
Inputs: limit, since, until. Returns: result
searchSearch meetingsARead-onlyIdempotent
Search the user's work calls: transcripts (who said what) and summaries (decisions, tasks, open questions).
Use it first when a question is about what was discussed, decided or agreed, who assigned or promised what, deadlines, the status of tasks and projects, or colleagues. People ask things like "What did we decide about pricing?", "What did Maya promise to send me?", "When did we last talk about the API migration?", "Did anyone push back on the Thursday release?" Matches words with different endings. Ranked by how many query words matched, then newest first. Then read what you found with get_meeting and get_transcript. Read-only.
Inputs: query (required), limit, since, until. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool targets a distinct retrieval mode: keyword search across content, chronological listing of meetings, full summary of one meeting, and verbatim transcript of one meeting. The search description explicitly routes the agent ('Use it first... Then read what you found with get_meeting and get_transcript'), and get_meeting vs get_transcript are cleanly separated by summary vs exact wording.
Three of four tools follow a clear verb_noun pattern (list_meetings, get_meeting, get_transcript). The bare 'search' lacks an object noun, a minor deviation but consistent with the otherwise verb-first convention and unlikely to confuse.
Four tools is a well-scoped surface for a read-only meeting-knowledge server: find, browse, summarize, and quote. Each tool covers a genuinely different access path with no filler.
The retrieval lifecycle is well covered, but the surface is entirely read-only: no way to create notes, mark tasks done, or draft follow-ups despite tasks and action items being first-class content in the summaries. Agents asking 'mark that task complete' hit a dead end.
Maintenance
Related MCP Connectors
Search and read your recorded meetings: notes, action items, participants, transcripts.
Read-only access to your RecordX meetings: search transcripts, summaries, action items.
Read-only access to your AIMochi meeting notes: list, search and read transcripts and summaries.
Your Microsoft Teams call transcripts, with real speaker names: search, read, ask.
Related MCP Servers
- AlicenseNot gradedqualityFmaintenanceProvides read-only access to Google Drive meeting transcripts and Google Calendar events, enabling AI assistants to search, analyze, and retrieve meeting insights.538 npm2MIT
- AlicenseNot gradedqualityCmaintenanceEnables MCP-capable agents to browse, search, and retrieve Meetily meeting transcripts and summaries on demand through read-only tools.1MIT
- AlicenseNot gradedqualityCmaintenanceEnables local, read-only keyword search across past Claude Code, Codex, Gemini CLI, and ChatGPT conversations plus markdown notes, with exact source citations and context retrieval.MIT
- AlicenseNot gradedqualityBmaintenanceProvides read-only access to what you have dictated and what was said in your recorded meetings, so coding agents like Codex, Claude Code, Pi or LM Studio can search your local transcripts and notes.MIT