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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_recent_documentsB | Get a list of recent Granola meeting documents |
| get_documentA | Get the content for a specific Granola document. Returns AI-generated notes by default, or raw transcript if requested. |
| search_documentsA | Search Granola documents by title pattern |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: listing recent documents, retrieving a specific document's content, and searching by title. There is no overlap or ambiguity between them.
Tool names follow a consistent verb_noun pattern ('get_' and 'search_'). Minor deviation exists between singular 'document' and plural 'documents', but overall naming is predictable and readable.
With only 3 tools, the server is well-scoped for its purpose of accessing meeting documents. Each tool earns its place and the count is appropriate for a focused read-only domain.
The server covers listing, retrieval, and search, which are the core read operations for meeting documents. While update/delete are absent, they are likely outside the intended scope, so the surface feels complete for its purpose.