OpenUSPublicDataMCP
Enables access to high-value US public data sources via MCP, including federal agencies, state portals, and platforms like Socrata, ArcGIS, and CKAN, with tools for searching, querying, and geographic resolution.
README
OpenUSPublicDataMCP
Federal-first, no-key-first MCP access to high-value US public data sources.
This is the US counterpart to OpenUKPublicDataMCP, but it deliberately separates federal coverage from the fragmented state and local ecosystem. Reusable Socrata, ArcGIS REST and CKAN adapters provide platform coverage without pretending that jurisdictions share one schema.
Current bootstrap status
- FastMCP server with stdio transport
- source registry with provenance metadata
health_checklist_public_data_sourcesfind_us_data_sources— filter the registry by jurisdiction or platformresolve_us_geography— resolve state names/abbreviations/city-state strings to state FIPSsearch_data_govagainst the official Data.gov CKAN API (endpoint under re-discovery after live 404)get_census_state_populationagainst the official Census ACS API (optional key)list_federal_agenciesagainst the official USAspending API (no key)search_federal_registeragainst the official Federal Register API (no key)search_usaspending_awardsagainst the official USAspending awards API (no key)search_congress_billsagainst the official Congress.gov API (optional key)search_socrata_catalogandquery_socrata_datasetquery_arcgis_feature_servicesearch_ckan_cataloglist_curated_state_portals— California, New York, Texas, Washington and Floridasearch_state_data— dispatch to the selected state's curated portal- mocked tests and project verification spine
Current status
Q2 2026 validation is complete: 16 tools, five curated state portal packs, stdio and Streamable HTTP transport, DynamicMCPProxy catalogue metadata, and 20 passing tests. See docs/tests/Q2-executive-report.md for the evidence-based executive snapshot.
Quick start
cd OpenUSPublicDataMCP
python3.11 -m venv .venv
. .venv/bin/activate
pip install -e '.[dev]'
pytest
fastmcp inspect src/openuspublicdata_mcp/server.py:mcp
fastmcp list src/openuspublicdata_mcp/server.py --json
fastmcp call src/openuspublicdata_mcp/server.py search_data_gov query='climate' limit=3 --json
Direction
- Curated state packs and local discovery.
- Federal breadth: BLS, BEA, NOAA, EPA, FDA, CDC and USDA.
- County FIPS, congressional districts and richer Census geography.
- HTTP deployment, DynamicMCPProxy and Hermes registration.
See docs/plans/2026-07-11-openuspublicdata-mcp-bootstrap.md and research/LINKS.md.
HTTP transport
OPENUS_PORT=8787 .venv/bin/openuspublicdata-http
curl http://127.0.0.1:8787/health
# MCP endpoint: http://127.0.0.1:8787/mcp
The DynamicMCPProxy catalogue entry is in integrations/dynamic-mcp-proxy-user-catalogue-entry.json. Hermes can use the stdio server directly:
hermes config set mcp_servers.openuspublicdata.command "/absolute/path/to/OpenUSPublicDataMCP/.venv/bin/python"
hermes config set mcp_servers.openuspublicdata.args '["-m", "openuspublicdata_mcp.server"]'
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.