# ai.memoket/memoket

- Registry name: `ai.memoket/memoket` · version 1.0.0
- Categories (automatic, keyword rules): Other
- Authentication at last check: No auth
- Declared risk: Read-only (all tools declare readOnlyHint)
- Capabilities (declared by the server): prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=ai.memoket%2Fmemoket
- Server page: https://mcpstation.net/s/ai.memoket--memoket.html

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

Memoket — access your recording transcripts, summaries, and key takeaways over MCP.

## Connect

- streamable-http: `https://mcp.memoket.ai/mcp`

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

- `get\_conversations`: \[metadata\_query\] Conversation-level metadata for the given conversation\_ids: id, title, started\_at, ended\_at, duration\_seconds, participants, language\_code. No transcript, brief, or summary body.
- `get\_transcripts\_by\_participant`: \[content\_fetch\] Transcript lines associated with participant\_ids in conversation\_ids. Turns participant metadata into transcript evidence for exposed search results.
- `get\_brief`: \[content\_fetch\] Per-conversation compact report body for the given conversation\_ids using Brief -\> Summary -\> Standard, where Standard is the first completed non-empty type=0 report.
- `get\_summaries`: \[content\_fetch\] Per-conversation summary body. With summary\_ids, fetch exact summary reports from search\_recordings. With conversation\_ids only, fetch the latest summary report for each conversation. Paginated \(offset\).
- `get\_transcripts`: \[content\_fetch\] Verbatim transcript of ONE recording; at most 100 lines / 4000 characters per page. Resume using both next\_offset and next\_text\_offset from the returned item, including within a long line.
- `list\_conversations`: \[metadata\_query\] List recordings by time window / participants. Returns id, title, started\_at, ended\_at, duration\_seconds, participants, language\_code \(no content\). Paginated \(count default 100, max 200; offset\). order\_by ranks within the window. NOTE: \`participants\` are speaker labels — placeholder
- `search\_recordings`: \[search\] Unified recording search. Runs bounded searches over transcript lines, topic segments, memory atoms, participant metadata, titles, briefs, summaries, and action items in one call. Returns typed hits plus conversation\_ids, line\_ids, segment\_ids, memory\_atom\_ids, participant\_ids, brief\_ids, s

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