How do I install the granolamcp mcp server?

Use a recorded configuration for your client, replace example credential values and paths, and verify the documented runtime. Restart or reconnect the client, then inspect the available tools.

What credentials does it need?

It reads `GRANOLA_CACHE_PATH` from the environment. Store these in your client's env block or a secrets manager — never commit them to a repository — and grant the narrowest scope that still covers your use case.

SSyncDev

Start a project

GranolaMCP MCP Server

A comprehensive Python library and CLI tool for accessing and analyzing Granola.ai meeting data, featuring a complete MCP (Model Context Protocol)

Local serverstdioPython

What is the GranolaMCP MCP Server?

A comprehensive Python library and CLI tool for accessing and analyzing Granola.ai meeting data, featuring a complete MCP (Model Context Protocol) server for AI

The short version

GranolaMCP provides complete access to Granola.ai meeting data through multiple interfaces:

What it needs from you

Python 3.12 or higher - No external dependencies (uses only Python standard library)

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

How to install the GranolaMCP MCP Server

{
  "mcpServers": {
    "granolamcp": {
      "command": "uvx",
      "args": ["granola-mcp"],
      "env": {
        "GRANOLA_CACHE_PATH": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

Python 3.12 or higher - No external dependencies (uses only Python standard library)

Variable	Description	Required
GRANOLA_CACHE_PATH	Filesystem location the server is allowed to use.	Optional

Frequently asked questions

A comprehensive Python library and CLI tool for accessing and analyzing Granola.ai meeting data, featuring a complete MCP (Model Context Protocol) server for AI Confirm the tools offered by your installed version in the connected client. Tool availability and permissions depend on the server and account configuration.