InfraNode

One shared HTTP client fans out to the upstream sources, each response is mapped into the canonical schema, license-gated with its attribution and cached in Redis (with stale-on-error fallback), then served through both a REST API and an MCP server. A failing upstream degrades tosource_status, it never fails the call.

Every category below is a REST endpoint under/api/v1/cities/{slug}/<key>. Over MCP the same data comes through 12 lean tools: a few named ones (get_city_overview,weather,air_quality,pois,compare, live boards) plus one genericget_city_resource(slug, resource=<key>)for every other data type (itsresourceenum lists all 67 keys).

- Keyless & read-only.No credentials, no writes, no user accounts.
- Canonical envelope.{ data, meta }with per-source status and attribution.
- Graceful degradation.A failing upstream returnssource_status, not an error.
- Safe by design.SSRF and injection gates validate every request; inputs are checked against fixed allowlists.

The same API is exposed as a remote MCP server, so AI agents can call all 67 data types as tools. One line with Claude Code:

claude mcp add --transport http infranode https://mcp.infranode.dev/mcp

Any other MCP client, point it at the remote endpoint (Streamable HTTP):

{ "mcpServers": { "infranode": { "url": "https://mcp.infranode.dev/mcp" } } }

- Cursor / Windsurf:add the block above to~/.cursor/mcp.json(or the app's MCP settings).
- VS Code:code --add-mcp '{"name":"infranode","url":"https://mcp.infranode.dev/mcp"}'
- Claude Desktop:add the samemcpServersblock to yourclaude_desktop_config.json.
- ChatGPT:add a connector with the URLhttps://mcp.infranode.dev/mcp.

Other MCP servers cover parts of the German or European data space. InfraNode is the broadest for city-level open data, and the projects below often complement each other:

You don't need to, the hosted endpoint above is the fastest path. But the code is open. Run the API stack locally with Docker (Compose v2):

cp .env.example .env # example config, contains NO real secrets docker compose -f deploy/docker-compose.yml up curl http://localhost/api/v1/health # -> {"status":"ok","version":"1.0.0","redis":true}

To run the MCP server itself locally over stdio (against the public API):

uv sync --group mcp INFRANODE_MCP_API_BASE=https://infranode.dev/api/v1 uv run python -m infranode.mcp.server

All settings use theINFRANODE_env prefix (see.env.example); each data source is toggled by its ownINFRANODE_ENABLE_*flag. Real secrets are never committed, only.env.exampleis versioned and CI runs a gitleaks scan.

Get water temperature and swimming conditions for the Aare river in Switzerland.

Global pollen forecasts for any city or coordinate, with per-species values for multiple plants and a multiple day outlook.

Provides advanced Formula 1 data analysis, including real-time telemetry, tire performance, weather prediction, and race strategy simulation.

Provides weather data using the Open-Meteo API.

Real-time surf, trails, volcano, ocean safety, weather, and restaurants for all Hawaiian islands — built for AI agents.

Access meteorological data for Portugal from the IPMA public API using natural language.

Provides live images, time-lapse videos, and current weather updates for Jade Dragon Snow Mountain.

Provides accurate Islamic prayer times for locations throughout Malaysia using the waktusolat.app API.

A collection of MCP servers for Cursor IDE, including demo and weather services.