Granola MCP Server

Semantic search and insight extraction for Granola meeting notes

README.md

granola-mcp

MCP server for semantic search across Granola meeting notes. Extracts insights, themes (pain-points, feature-requests, decisions, etc.), and key quotes with speaker attribution. Uses LanceDB for fast local vector search.

Based on reverse engineering research by Joseph Thacker and getprobo.

Features

  • Export: Extract all your Granola meetings with transcripts
  • Semantic Search: Vector-indexed search across meetings with pre-extracted insights
  • Speaker Attribution: Distinguishes between host (me) and participants
  • Theme Extraction: Auto-categorizes content into themes (pain-points, feature-requests, etc.)
  • MCP Server: Exposes search to Claude Code, Claude Desktop, and other AI tools

Prerequisites

  • Node.js 18+
  • Granola desktop app installed and logged in
  • OpenAI API key (for embeddings and insight extraction)

Installation

npm install
npm run build

Quick Start

# One command to sync everything (export + index)
OPENAI_API_KEY=sk-... node dist/index.js sync

# Or with a custom data directory
OPENAI_API_KEY=sk-... node dist/index.js sync ./my-data

# Test search
OPENAI_API_KEY=sk-... node dist/index.js search "user pain points"

CLI Commands

Sync (Recommended)

The easiest way to keep your data up to date - exports from Granola and rebuilds the index in one step:

OPENAI_API_KEY=sk-... node dist/index.js sync

# With options
OPENAI_API_KEY=sk-... node dist/index.js sync ./my-data
OPENAI_API_KEY=sk-... node dist/index.js sync --skip-extraction  # Faster, reuses existing insights

Export from Granola

Export only (without indexing):

node dist/index.js export ./output
node dist/index.js export ./output --format markdown
node dist/index.js export ./output --format json

Build Search Index

# Full indexing with insight extraction (~$0.02/document)
OPENAI_API_KEY=sk-... node dist/index.js index ./export

# Skip extraction (use existing insights, just rebuild embeddings)
OPENAI_API_KEY=sk-... node dist/index.js index ./export --skip-extraction

Search from CLI

OPENAI_API_KEY=sk-... node dist/index.js search "pricing concerns"
OPENAI_API_KEY=sk-... node dist/index.js search "feature requests" --folder "User interviews"

Export for ChatGPT

OPENAI_API_KEY=sk-... node dist/index.js export-combined ./chatgpt.md
OPENAI_API_KEY=sk-... node dist/index.js export-combined ./chatgpt.md --query "user feedback"

Other Commands

node dist/index.js list              # List documents
node dist/index.js workspaces        # List workspaces
node dist/index.js folders           # List folders
node dist/index.js transcript <id>   # Get specific transcript

MCP Server Setup

Claude Code

Add to .mcp.json in your project:

{
  "mcpServers": {
    "granola": {
      "type": "stdio",
      "command": "node",
      "args": ["/path/to/granola-mcp/dist/mcp/server.js"],
      "env": {
        "GRANOLA_DATA_DIR": "/path/to/granola-mcp/export",
        "OPENAI_API_KEY": "sk-..."
      }
    }
  }
}

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "granola": {
      "command": "node",
      "args": ["/path/to/granola-mcp/dist/mcp/server.js"],
      "env": {
        "GRANOLA_DATA_DIR": "/path/to/granola-mcp/export",
        "OPENAI_API_KEY": "sk-..."
      }
    }
  }
}

MCP Tools

Tool Description
search Semantic search across meetings, returns summaries + quotes
search_themes Find documents by theme (pain-points, feature-requests, etc.)
list_folders List all folders with document counts
list_documents List documents with brief summaries
get_document Get full document details (all themes + quotes)
get_transcript Get raw transcript (use sparingly)
get_themes List available themes with definitions

Speaker Attribution

The system distinguishes between speakers:

  • speaker: "me" - The meeting host (you)
  • speaker: "participant" - Other people in the meeting

This helps AI understand what's your own idea vs external feedback.

Pre-defined Themes

  • pain-points: User frustrations, problems, complaints
  • feature-requests: Desired features, wishlist items
  • positive-feedback: What users liked, praised
  • pricing: Cost concerns, value perception
  • competition: Competitor mentions, alternatives
  • workflow: How users currently do things
  • decisions: Key decisions made, action items
  • questions: Open questions needing clarification

Output Structure

export/
├── vectors.lance/           # LanceDB vector index
├── Meeting_Title_1/
│   ├── document.json        # Raw document data
│   ├── notes.md

Tools 7

searchSemantic search across meetings, returns summaries and quotes
search_themesFind documents by theme like pain-points or feature-requests
list_foldersList all folders with document counts
list_documentsList documents with brief summaries
get_documentGet full document details including all themes and quotes
get_transcriptGet raw transcript for a specific document
get_themesList available themes with definitions

Environment Variables

OPENAI_API_KEYrequiredAPI key for embeddings and insight extraction
GRANOLA_DATA_DIRrequiredPath to the exported Granola data directory

Try it

Search for all user pain points mentioned in my recent meetings.
What are the top feature requests from the last three customer interviews?
List all folders in my Granola workspace and tell me which one has the most documents.
Get the full details and key quotes for the meeting titled 'Q3 Product Strategy'.
Show me the definition of the 'pricing' theme and find meetings where it was discussed.

Frequently Asked Questions

What are the key features of Granola MCP?

Semantic search across meeting transcripts using LanceDB. Auto-categorization of content into themes like pain-points and decisions. Speaker attribution to distinguish between host and participants. Export functionality for Granola meetings to markdown or JSON. Integration with Claude Desktop and Claude Code.

What can I use Granola MCP for?

Product managers identifying recurring user pain points across multiple customer calls.. Sales teams quickly retrieving pricing concerns or competitor mentions from past meetings.. Engineering leads extracting action items and decisions from technical syncs.. Researchers synthesizing feedback from a large volume of qualitative interview transcripts..

How do I install Granola MCP?

Install Granola MCP by running: npm install && npm run build

What MCP clients work with Granola MCP?

Granola MCP works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep Granola MCP docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Open Conare