FirstData
The World's Most Comprehensive, Authoritative, and Structured Open Source Data Source Knowledge Base
claude mcp add --transport stdio mlt-oss-firstdata node server.js
How to use
FirstData MCP provides an integrated, authority-backed data source navigation experience. It helps users locate primary sources from governments and international organizations, discover structured metadata, and retrieve direct access paths (URLs, APIs, and download options) with a clear evidence trail. The built-in Source Locator suggests top data sources based on natural language queries, then delivers concise recommendations with provenance and access details. The Site Pathfinder offers step-by-step navigation instructions for complex data portals, including exact pages to click, filters to apply, and data formats to download, ensuring you can reproduce results and audit the data lineage. This combination enables researchers, policy-makers, and analysts to move from vague questions to precise, citable data paths in a few minutes rather than hours.
How to install
Prerequisites:
- Node.js (v12+ recommended) and npm installed on your system
- Internet access to install dependencies and fetch data sources
Installation steps:
-
Clone the repository: git clone https://github.com/MLT-OSS/FirstData.git cd FirstData
-
Install dependencies: npm install
-
Configure environment (optional):
- Create a .env file if your deployment requires API keys or custom endpoints
- Example (not required for local run): API_BASE_URL=https://api.firstdata.example AUTH_TOKEN=your_token_here
-
Start the MCP server: npm run start
-
Test the server (optional): curl http://localhost:3000/health
Notes:
- The exact start command may vary by deployment. If you have a custom startup script, adjust the mcp_config accordingly.
- For production, consider containerizing the server or deploying behind a reverse proxy.
Additional notes
Tips and commonly encountered issues:
- Ensure Node.js is at least v12+ to avoid compatibility issues with modern dependencies.
- If the server struggles to fetch data sources, check network access to data portals; some sources restrict automated access.
- Maintain a current list of trusted data sources; the MCP uses authoritative flags (government, international, research, market, commercial) to rank results.
- When using the Site Pathfinder, always verify that steps reflect the current portal UI, as government and international portals frequently update layouts.
- Monitor updates to the underlying data schemas (datasource-schema.json) to ensure metadata remains machine-readable and verifiable.
Related MCP Servers
lihil
2X faster ASGI web framework for python, offering high-level development, low-level performance.
ReActMCP
ReActMCP is a reactive MCP client that empowers AI assistants to instantly respond with real-time, Markdown-formatted web search insights powered by the Exa API.
jmeter
✨ JMeter Meets AI Workflows: Introducing the JMeter MCP Server! 🤯
example
A ready-to-use MCP (Model Context Protocol) server template for extending Cursor IDE with custom tools. Deploy your own server to Heroku with one click, create custom commands, and enhance your Cursor IDE experience. Perfect for developers who want to add their own tools and commands to Cursor IDE without complex setup.
pfsense
pfSense MCP Server enables security administrators to manage their pfSense firewalls using natural language through AI assistants like Claude Desktop. Simply ask "Show me blocked IPs" or "Run a PCI compliance check" instead of navigating complex interfaces. Supports REST/XML-RPC/SSH connections, and includes built-in complian
cloudwatch-logs
MCP server from serkanh/cloudwatch-logs-mcp