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"]'
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。