MeetGeek MCP Server — Quick & Easy Guide
The MeetGeek MCP Server is an official, local bridge that lets MCP‑compatible AI tools (like Claude Desktop, Cursor, LobeChat, etc.) access your MeetGeek meeting data—transcripts, summaries, action items, highlights—directly from your machine. It implements the Model Context Protocol (MCP) and connects securely to the MeetGeek API using your API key.
1. Why Use the MCP Server?
Runs locally—nothing is sent to third parties.
Standardized across multiple clients—configure once, use anywhere.
Enables agent prompts like “Summarise last week’s onboarding meetings,” or “List all open action items from my team syncs.”
2. Requirements
Node.js v14 or newer
A valid MeetGeek API key (found under your MeetGeek Settings → Integrations → Public API)
(Optional) MEETGEEK_BASE_URL if using a custom MeetGeek deployment
3. Setup Steps
Clone the repository:
git clone https://github.com/meetgeekai/meetgeek-mcp-server
cd meetgeek-mcp-server
Install dependencies and build:
npm install
npm run build
3. Run the server:
MEETGEEK_API_KEY=your_key_here node dist/index.js
4. Configure Your AI Client
Add the MCP server to your client configuration. For example:
{
"mcpServers": {
"meetgeek": {
"command": "node",
"args": ["path/to/dist/index.js"],
"env": {
"MEETGEEK_API_KEY": "your_key_here",
"MEETGEEK_BASE_URL": "https://api.meetgeek.ai"
}
}
}
}
Different clients may require different formatting—check their docs. Once configured, restart the client to enable tools.
5. Tools You Can Use
Tool Name | Description |
| Filter meetings by date, tag, participants, etc. |
| Detailed metadata on a specific meeting |
| Full transcript with speakers & timestamps |
| AI-generated summary in chosen length |
| Structured action‑item list with due dates |
| Automated meeting highlights and quotes |
6. Basic Troubleshooting
“Module not found” errors → run
npm installin project root.
Invalid API key errors or exits → re-check your key under MeetGeek account settings.
Client doesn't see tools → ensure the server is running after build, and STDIO isn't redirected or suppressed.
7. Want More Info?
The repository README includes advanced instructions like:
Docker and container support
Alternative transport (SSE) options
Debugging and logging flags
Full TypeScript source code and example usage
You’ll find the complete guide and setup details in the GitHub repository:
TL;DR (Step by Step)
Clone the repo
npm install → npm run build
Launch server with your
MEETGEEK_API_KEY
Add entry to your MCP‑client config
Restart your AI tool → Ask questions directly in chat