GraphAPI MCP
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@GraphAPI MCPlist my 5 most recent emails"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
graph-mcp
Minimal Python MCP server that exposes one tool, graphapi, for authenticated Microsoft Graph API calls through a RequestRocket proxy.
Setup
pip install -r requirements.txtCopy .env.example to config.env or .env in this directory (same folder as server.py) and set:
GRAPH_API_REQUESTROCKET_URL— proxy base URL (no trailing slash required; it is stripped)GRAPH_API_REQUESTROCKET_KEY— authorization value sent as theAuthorizationheader
Alternatively, set those variables in your environment. To load credentials from another file (for example Cowork’s config.env), set:
export DOTENV_PATH=/path/to/config.envRun
python server.pyThe server uses stdio transport (FastMCP default). On startup it logs the proxy URL and tool signature to stdout.
Tool: graphapi
Argument | Description |
|
|
| Graph path such as |
| Optional query parameters (e.g. |
| Optional JSON body for |
Successful responses return {"status": <code>, "data": ...} where data is parsed JSON or plain text if the body is not JSON. HTTP errors return {"status": <code>, "error": "<body>"}. Connection failures return {"error": "<message>"}.
Cowork (local MCP)
Add a local MCP connector:
python /path/to/graph-mcp/server.pyIf credentials live elsewhere, set DOTENV_PATH to that file, for example:
DOTENV_PATH=/Users/you/project/config.envRequirements
See requirements.txt: mcp[cli], httpx, python-dotenv, pydantic.
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/geoicons/graphapi-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server