mcp-obo
Implements the on-behalf-of flow with Entra ID to enable authorized calls to Microsoft Graph API via MCP tools.
README
On-behalf-of flow with Entra ID and FastMCP
Blog post: https://baeke.info/2025/07/29/end-to-end-authorization-with-entra-id-and-mcp/
Instructions
1. Create and activate a Python virtual environment
python3 -m venv .venv
source .venv/bin/activate
2. Install dependencies
pip install -r requirements.txt
3. Set up environment variables
Create a .env file in the project root with the required Azure and API credentials (see example files for required variables).
4. Start the MCP server
python -m mcp.main
5. Run the MCP client
In a new terminal (with the virtual environment activated):
python mcp_client.py
Diagrams
sequenceDiagram
autonumber
participant User
participant Client
participant AzureAD as "Azure Entra ID"
participant MCP
participant MSGraph
User->>Client: Initiate Device Flow
Client->>AzureAD: Start Device Code Flow
AzureAD-->>Client: Device Code + Verification URL
Client->>User: Show Code + URL
User->>AzureAD: Authenticates via browser
AzureAD-->>Client: Returns Access Token (for MCP)
Client->>MCP: Call tool with Bearer Access Token
MCP->>AzureAD: OBO request for token to call MS Graph\n(include access token as assertion)
AzureAD-->>MCP: Returns new Access Token (for MS Graph)
MCP->>MSGraph: Call Graph API with new token
MSGraph-->>MCP: Graph data
MCP-->>Client: Return tool result
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
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.