Provides Model Context Protocol integration for querying and visualizing OpenStreetMap data with web-based maps, PostgreSQL/PostGIS support, and interactive MCP tools for map control and spatial data management.
Unlock the full potential of OSM PostgreSQL Server through LangDB's AI Gateway. Get enterprise-grade security, analytics, and seamless integration with zero configuration.
Free tier available • No credit card required
This package provides OpenStreetMap integration for MCP, allowing users to query and visualize map data through an MCP interface.
This is my claude_desktop_config.json
:
{ "mcpServers": { "OSM PostgreSQL Server": { "command": "/Users/wiseman/.local/bin/uv", "args": [ "run", "--env-file", ".env", "--with", "mcp[cli]", "--with", "psycopg2", "--with-editable", "/Users/wiseman/src/mcp-osm", "--directory", "/Users/wiseman/src/mcp-osm", "mcp", "run", "mcp.py" ] } } }
When the MCP server starts it also starts a web server at http://localhost:8889/ that has the map interface.
The following environment variables can be used to configure the MCP:
FLASK_HOST
- Host for the Flask server (default: 127.0.0.1)FLASK_PORT
- Port for the Flask server (default: 8889)PGHOST
- PostgreSQL host (default: localhost)PGPORT
- PostgreSQL port (default: 5432)PGDB
- PostgreSQL database name (default: osm)PGUSER
- PostgreSQL username (default: postgres)PGPASSWORD
- PostgreSQL password (default: postgres)The following MCP tools are available:
get_map_view
- Get the current map viewset_map_view
- Set the map view to specific coordinates or boundsset_map_title
- Set the title displayed at the bottom right of the mapadd_map_marker
- Add a marker at specific coordinatesadd_map_line
- Add a line defined by a set of coordinatesadd_map_polygon
- Add a polygon defined by a set of coordinatesquery_osm_postgres
- Execute a SQL query against the OpenStreetMap databaseDiscover shared experiences
Shared threads will appear here, showcasing real-world applications and insights from the community. Check back soon for updates!