Memoket

By Memoket AI

Get New App Alerts

Open in ChatGPT

Open in Claude

Overview

Memoket MCP connects your meeting recordings to Claude so you can ask questions about conversations you've already captured. Once connected, Claude can pull up your list of recordings, retrieve auto-generated summaries with key points and takeaways, and reference full transcripts to answer questions grounded in exactly what was said. The connector is read-only: it can find and read your existing recordings, transcripts, and summaries, but it cannot create, edit, or delete anything in your Memoket account. It exposes three retrieval tools — list recordings, get summaries, and get transcripts. Connection uses a browser-based OAuth sign-in to your Memoket account — no API keys to manage. Your data is accessed only when a question requires it, and the server is designed to redact sensitive details such as payment card numbers, government IDs, credentials, and health information before any content is returned. You can revoke access at any time from Claude's connector settings or your Memoket account.

Tools

get_brief

ChatGPT

[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_conversations

ChatGPT

[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_summaries

ChatGPT

[content_fetch] Per-conversation summary body for the given conversation_ids (the user-visible summary). Paginated (offset).

get_transcripts

ChatGPT

[content_fetch] Verbatim transcript of ONE recording by conversation_id. Paginated (offset / next_offset) — page through for more.

get_transcripts_by_participant

ChatGPT

[content_fetch] Transcript lines associated with participant_ids in conversation_ids. Turns participant metadata into transcript evidence for exposed search results.

list_conversations

ChatGPT

[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 — placeholders ('Speaker A/B') unless the user tagged them, not necessarily real names.

search_recordings

ChatGPT

[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, summary_ids, action_item_ids. Chat execution expands hits into readable evidence automatically; external callers can fetch returned ids where a matching fetcher is advertised.