Plaud MCP Server ★ New (July 4)¶
Overview¶
Plaud MCP connects AI agents to your Plaud.ai recording library. Plaud is an AI-powered voice recorder that captures meetings, calls, and conversations - then transcribes and summarizes them. With the MCP server, agents can search your recording history, pull full transcripts, generate summaries, and extract action items from any conversation you've captured.
Key advantage: Your AI assistant gains access to every conversation you've recorded. Ask "what was the client's feedback on the Q3 roadmap?" and get answers grounded in actual meeting transcripts, not memory.
Key Features¶
- Recording search: Full-text search across all recordings, transcripts, and summaries
- Transcript retrieval: Pull complete transcripts with speaker labels and timestamps
- Document generation: Create meeting notes, summaries, and action-item lists from recordings
- Cross-recording analysis: Find patterns, recurring topics, and commitments across multiple recordings
- AI-powered summaries: Generate concise summaries of any recording via the Plaud AI engine
- Remote endpoint: Hosted MCP server - connect directly, no local installation needed
Installation¶
# Add to Hermes (remote SSE endpoint)
hermes mcp add plaud --url https://api.plaud.ai/mcp
Configuration¶
- Obtain your Plaud API credentials from docs.plaud.ai
- Add the remote endpoint to your MCP client configuration
- Authenticate via OAuth - your client will open a browser for one-time authorization
Tools¶
14 tools, all prefixed plaud_.
| Tool | Description |
|---|---|
plaud_list_files |
List recordings, optionally filtered by transcription status |
plaud_get_file |
Get detailed metadata for a specific file |
plaud_search_files |
Search recordings by keyword or date range |
plaud_get_transcript |
Fetch raw or polished transcript text |
plaud_get_summary |
Fetch AI-generated summary |
plaud_export_transcript |
Export transcript as TXT or SRT with optional timestamps |
plaud_generate |
Generate transcript and summary for a file |
plaud_name_speakers |
Rename speakers in a transcript |
plaud_rename_file |
Rename a single file |
plaud_batch_rename |
Rename multiple files at once (rate-limited) |
plaud_move_to_folder |
Move a file to a folder |
plaud_list_folders |
List all folders and tags |
plaud_trash_file |
Move a file to trash |
plaud_get_user |
Get current user profile |
Use Cases for Operators¶
- Client call intelligence: Before a follow-up call, ask your agent "what did we promise Acme Corp in our last three calls?" - it searches your Plaud recordings and surfaces commitments
- Meeting prep: "Summarize all conversations about the pricing change from the last two weeks"
- Knowledge preservation: Every customer call, team standup, and partner meeting becomes a searchable knowledge asset
- Cross-functional alignment: "Find every mention of the API migration across all recordings this month"
Why Operators Need This¶
Operators spend 40%+ of their time in meetings. Most of those insights evaporate within 48 hours. Plaud MCP turns every recorded conversation into a persistent, queryable memory that your AI assistant can draw on - so you stop forgetting decisions and start building on them.
Discovered via mcpservers.org - July 4, 2026 ← External MCP Catalog | Plaud MCP Docs →
Integration with CorpusIQ¶
CorpusIQ is the connector layer that lets AI assistants read the systems a business already runs on - accounting, payments, CRM, email, files and analytics - and answer with the source named. It is read-only by design: it retrieves data and never writes to, or acts in, a connected system, which is what makes it safe to point at live accounts.
This page is part of the CorpusIQ directory, the reference we maintain for the MCP server and agent-skill ecosystem. Run alongside CorpusIQ, a third-party server like this one can be combined with a company's own business data in a single answer.