Granola
Enables semantic search and insight extraction across Granola meeting notes, categorizing content into themes like pain points and decisions. It provides AI assistants with tools to query meeting transcripts, summaries, and speaker-attributed quotes
What is Granola?
Granola is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables semantic search and insight extraction across granola meeting notes, categorizing content into themes like pain points and decisions. it provides ai assistants with tools to query meeting tran...
Enables semantic search and insight extraction across Granola meeting notes, categorizing content into themes like pain points and decisions. It provides AI assistants with tools to query meeting transcripts, summaries, and speaker-attributed quotes
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Enables semantic search and insight extraction across Granol
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx granolaConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Granola
The Granola MCP Server connects AI assistants to your Granola meeting notes, enabling semantic search, transcript retrieval, and insight extraction across all your recorded meetings. It exposes eight read-only tools that let you list, search, and retrieve full meeting notes with transcripts and speaker attribution, categorize content into themes like pain points and decisions, and query meetings by date range — giving your AI assistant a searchable memory of every conversation you've had. The server is built in Python using uv and requires a Granola Business or Enterprise plan for API access.
Prerequisites
- Python 3.10+ and uv installed (https://docs.astral.sh/uv/getting-started/installation/)
- A Granola Business or Enterprise account with a Personal API key (grn_*) from Settings → API in the Granola desktop app
- Dedalus platform API key (dsk_*) if using Dedalus integration features
- An MCP-compatible client such as Claude Desktop
Clone the repository and install dependencies
Clone the granola-mcp repository and use uv to sync the project dependencies.
git clone https://github.com/NickyHeC/granola-mcp.git
cd granola-mcp
uv syncSet your environment variables
Create a .env file or set environment variables with your Granola API key and optional Dedalus credentials. The GRANOLA_API_KEY is mandatory.
GRANOLA_API_KEY=grn_your_granola_api_key
DEDALUS_API_KEY=dsk_your_dedalus_key
DEDALUS_API_URL=https://api.dedaluslabs.ai
DEDALUS_AS_URL=https://as.dedaluslabs.ai
GRANOLA_MCP_SLUG=nickyhec/granola-mcpTest the server locally
Run the MCP server to verify it starts and can reach the Granola API.
uv run src/main.pyAdd the server to your MCP client configuration
Configure Claude Desktop or your MCP client to run the granola-mcp server using uv. Use the absolute path to the cloned repository.
{
"mcpServers": {
"granola": {
"command": "uv",
"args": ["run", "/absolute/path/to/granola-mcp/src/main.py"],
"env": {
"GRANOLA_API_KEY": "grn_your_granola_api_key"
}
}
}
}Restart your MCP client and query your meetings
Restart Claude Desktop so it connects to the granola-mcp server. You can now ask Claude to search, summarize, and extract insights from your Granola meeting notes.
Granola Examples
Client configuration
Claude Desktop MCP configuration for the Granola server. Replace the path and API key with your actual values.
{
"mcpServers": {
"granola": {
"command": "uv",
"args": ["run", "/Users/you/granola-mcp/src/main.py"],
"env": {
"GRANOLA_API_KEY": "grn_your_key_here"
}
}
}
}Prompts to try
Example queries to extract insights from your Granola meeting archive.
- "What meetings did I have this week? Summarize the key decisions made."
- "Search my meeting notes for any discussion about pricing strategy."
- "Get the full transcript from my meeting with the engineering team on Monday."
- "List all pain points mentioned in meetings from the past month."
- "What action items were assigned to me across all meetings last week?"
- "Find all meetings where Sarah spoke and summarize her contributions."Troubleshooting Granola
API returns 401 Unauthorized with a valid-looking GRANOLA_API_KEY
Granola Personal API keys require a Business or Enterprise plan. Free and Pro plan accounts cannot generate API keys. Verify your plan in the Granola desktop app under Settings → Subscription.
Tools return no results for recent meetings
Granola MCP only returns notes that have been fully processed by Granola AI (summarized and transcribed). Very recent meetings may still be processing. Wait a few minutes after the meeting ends for the notes to be available.
Rate limit errors (429) when querying many meetings
The Granola API enforces a burst limit of 25 requests and 5 requests/second sustained. Add delays between bulk queries or use the paginated tools (granola_list_notes_paginated) which handle pagination automatically.
Frequently Asked Questions about Granola
What is Granola?
Granola is a Model Context Protocol (MCP) server that enables semantic search and insight extraction across granola meeting notes, categorizing content into themes like pain points and decisions. it provides ai assistants with tools to query meeting transcripts, summaries, and speaker-attributed quotes It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Granola?
Follow the installation instructions on the Granola GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Granola?
Granola works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Granola free to use?
Yes, Granola is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Granola Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Granola? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Granola in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Granola?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.