Fannie Mae MCP
Enables querying Fannie Mae's public APIs, currently supporting loan limits retrieval for US counties and territories via OAuth2.
README
Fannie Mae MCP
A remote MCP server exposing Fannie Mae's public APIs, starting with the Loan Limits API. Uses OAuth2 client-credentials against Fannie Mae's PingOne authorization server -- no user-facing OAuth flow needed, just a client ID and secret from the Developer Portal.
Tools exposed:
list_apis— catalog of all 16 public APIs (only Loan Limits is wired to live data so far)get_all_loan_limits— loan limits for every US county/territoryget_historical_loan_limits— loan limits for a given calendar year (2009-2019)get_loan_limits_by_county— loan limits for one specific state + county
1. Prerequisites
- A Fannie Mae Developer Portal account with an approved app for the Loan Limits API (Public APIs category)
- Your app's client ID and client secret
- The token endpoint URL shown on the portal's "Create Access Token" step (PingOne URL specific to your app)
- A Vercel account
2. Push to GitHub
git init
git add .
git commit -m "Initial commit"
git remote add origin git@github.com:<you>/fannie-mae-mcp.git
git push -u origin main
3. Import into Vercel
- Go to vercel.com/new → Import Git Repository → select this repo
- In Environment Variables, add
FANNIE_CLIENT_ID,FANNIE_CLIENT_SECRET, andFANNIE_TOKEN_URL - Click Deploy
Every future git push to main auto-deploys.
4. Connect it to Claude / Cowork
Add a custom connector pointing at:
https://<your-vercel-domain>/api/mcp
Then try: "List the Fannie Mae APIs available, then get loan limits for Los Angeles County, CA."
Local development
npm install
cp .env.example .env.local # fill in your credentials
npm run dev
Notes
- Access tokens expire after 1 hour and are cached in memory per warm serverless instance; a cold start just fetches a fresh one automatically.
- Only Loan Limits is implemented so far. The other 15 catalog entries in
list_apisare for browsing/reference -- extending to a new API means pulling its own Swagger docs first (base path, params, response shape) before wiring it up, the same way Loan Limits was built.
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.