Granola MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {
"tasks": {
"list": {},
"cancel": {},
"requests": {
"tools": {
"call": {}
},
"prompts": {
"get": {}
},
"resources": {
"read": {}
}
}
}
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_meetingsA | Search meeting notes by keyword or phrase. Args: query: Search query (keywords or phrase) limit: Maximum results to return (default: 10) date_from: Filter by start date (YYYY-MM-DD) date_to: Filter by end date (YYYY-MM-DD) attendee: Filter by attendee name or email ctx: MCP context Returns: Search results with matching documents |
| get_meetingA | Get complete meeting details including notes and summaries. Args: meeting_id: Meeting document ID include_transcript: Include full transcript in notes_plain field ctx: MCP context Returns: Full meeting details with notes, attendees, and AI panels |
| list_meetingsB | List meetings with optional filters. Args: limit: Maximum results (default: 20) offset: Skip first N results date_from: Filter by start date (YYYY-MM-DD) date_to: Filter by end date (YYYY-MM-DD) attendee: Filter by attendee name or email sort: Sort order - date_desc, date_asc, or title ctx: MCP context Returns: Paginated list of meetings |
| search_by_personA | Find all meetings involving a specific person. Args: person: Person's name or email address limit: Maximum results (default: 20) date_from: Filter by start date (YYYY-MM-DD) date_to: Filter by end date (YYYY-MM-DD) ctx: MCP context Returns: List of meetings with that person |
| get_transcriptA | Get the full transcript for a meeting. Args: meeting_id: Meeting document ID format: Output format - text or timestamped ctx: MCP context Returns: Transcript segments with timing information |
| summarize_meetingsA | Get meeting summaries with notes for a time period. Use this when asked to summarize, recap, or review meetings over a period. Provide either date_from/date_to (YYYY-MM-DD) or days (last N days). Args: date_from: Start date (YYYY-MM-DD) date_to: End date (YYYY-MM-DD) days: Convenience shortcut: last N days from today person: Filter by attendee name or email ctx: MCP context Returns: Meetings with their notes and attendees |
| extract_action_itemsA | Extract action items from meeting notes. Use this when asked for action items, TODOs, or next steps. Can target a single meeting by ID, or scan multiple meetings by date range. Args: meeting_id: Specific meeting ID to extract from (takes precedence) date_from: Start date (YYYY-MM-DD) for scanning multiple meetings date_to: End date (YYYY-MM-DD) for scanning multiple meetings days: Convenience shortcut: last N days from today person: Filter by attendee name or email (only with date range) ctx: MCP context Returns: Extracted action items with source meeting context |
| get_meeting_statsA | Get statistics about your Granola meeting data. Args: ctx: MCP context Returns: Statistics including document counts, date range, and unique attendees |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| granola_skill | How to effectively use this server's tools. |
TDQS
Scored across 8 tools
Most tools are distinct, but `list_meetings` and `search_by_person` both return lists of meetings with attendee filters, creating potential confusion. Descriptions help differentiate but overlap exists.
All tool names follow a consistent verb_noun pattern using snake_case (e.g., `list_meetings`, `get_meeting`, `search_meetings`). No mixed conventions or vague verbs.
8 tools is well-scoped for a meeting notes query server. Each tool serves a clear purpose without unnecessary bloat or insufficiency.
Covers core querying needs: retrieve, list, search, summarize, extract action items, stats. Missing update/delete (likely out of scope) and a combined view of all action items, but minor gaps agents can work around.