What is Mcp Census Server

mcp_census_server is a robust Model Context Protocol (MCP) server designed to access data from the US Census Bureau via JSON-RPC over HTTP.

Use cases

Use cases for mcp_census_server include retrieving demographic data for analysis, integrating Census data into applications, and providing data access for research projects.

How to use

To use mcp_census_server, clone the repository, set up your environment variables with your API keys, install the dependencies, and start the server. You can then send JSON-RPC requests to the server endpoint with the required headers.

Key features

Key features include support for JSON-RPC 2.0, Pydantic models for request/response validation, caching of Census API responses, structured logging, API key authentication, a health check endpoint, and interactive API documentation via Swagger UI.

Where to use

mcp_census_server can be used in various fields that require access to US Census Bureau data, including research, data analysis, and application development.

MCP Census Server

A robust Model Context Protocol (MCP) server for accessing US Census Bureau data via JSON-RPC over HTTP.

Features

• JSON-RPC 2.0 (single and batch requests)
• Pydantic models for request/response validation
• Caching of Census API responses (TTL 5 minutes)
• Structured logging (via Python logging)
• API key authentication via X-API-Key header
• Health check endpoint (/health)
• Interactive API docs (Swagger UI available at /docs)
• MCP methods:
  • initialize: negotiate protocol version and capabilities
  • notifications/initialized: client ready notification
  • tools/list: list available tools (census/get)
  • tools/call: invoke census/get to retrieve Census Bureau data

Quickstart

1. Clone the repository and enter the directory:

   git clone https://github.com/kaman1/mcp_census_server.git
   cd mcp_census_server
   

2. Copy the environment template and set your keys:

   cp .env.example .env
   # Edit .env:
   # CENSUS_API_KEY=<your_census_api_key>
   # SERVER_API_KEY=<your_mcp_server_secret_key>
   

3. Install dependencies:

   pip install -r requirements.txt
   

4. Start the server:

   uvicorn app:app --host 0.0.0.0 --port 8000 --reload
   

5. Send JSON-RPC requests to http://localhost:8000/ with header X-API-Key: <SERVER_API_KEY>.

Example tools/list call:

curl -X POST http://localhost:8000/ \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $SERVER_API_KEY" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

Development

• Tests: pytest
• Formatting: black .
• Imports: isort .
• Linting: flake8 .
• CI pipeline configured in .github/workflows/ci.yml

Documentation

• Architecture: docs/architecture.md
• Usage Examples: docs/usage.md
• Authentication: docs/authentication.md
• Styled Documentation (MDX + Mintlify):

  npm install
  npm run serve:docs
  

Hosted Documentation

You can publish these docs via GitHub Pages:

1. In your GitHub repository, go to Settings > Pages.
2. Under Source, choose the main branch and /docs folder.
3. Click Save.

The docs will be available at:

https://<username>.github.io/mcp_census_server/

You can add this URL in the repository About section as the project website.

Client Application

The client/ directory contains a Next.js-based MCP client that can interact with this server.

1. Change into the client folder:

   cd client
   

2. Copy the example environment file and fill in your keys and server URL:

   cp .env.example .env.local
   # Set OPENAI_API_KEY, MCP_SERVER_URL (e.g. https://your-server), SERVER_API_KEY
   

3. Install dependencies and start the development server:

   npm install
   npm run dev
   

4. Open http://localhost:3000 to use the client UI.

Quick Start Script

You can configure environments and launch both server and client in one step:

chmod +x start.sh
./start.sh

This will prompt for all required keys and run the MCP server and client concurrently.