GraphAPI MCP
A Python-based MCP server that enables authenticated Microsoft Graph API calls through a RequestRocket proxy. It provides a single tool to interact with Microsoft services using standard HTTP methods and Graph API paths.
README
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.txt
Copy .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.env
Run
python server.py
The server uses stdio transport (FastMCP default). On startup it logs the proxy URL and tool signature to stdout.
Tool: graphapi
| Argument | Description |
|---|---|
method |
GET, POST, PATCH, PUT, or DELETE |
path |
Graph path such as /me/messages. A leading https://graph.microsoft.com/v1.0 prefix is stripped. |
params |
Optional query parameters (e.g. {"$top": 10}) |
body |
Optional JSON body for POST / PATCH / PUT |
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.py
If credentials live elsewhere, set DOTENV_PATH to that file, for example:
DOTENV_PATH=/Users/you/project/config.env
Requirements
See requirements.txt: mcp[cli], httpx, python-dotenv, pydantic.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.