OpenStreetMap MCP Server

OpenStreetMap MCP Server

Enhancing LLMs with geospatial and location-based capabilities via the Model Context Protocol.

View on GitHub
134
Stars
30
Forks
134
Watchers
8
Issues
OpenStreetMap MCP Server enables large language models to interact with rich geospatial data and location-based services through a standardized protocol. It provides APIs and tools for address geocoding, reverse geocoding, points of interest search, route directions, and neighborhood analysis. The server exposes location-related resources and tools, making it compatible with MCP hosts for seamless LLM integration.

Key Features

Address geocoding and reverse geocoding
Finding nearby points of interest
Route direction and navigation processing
Searching for specific place categories within a region
Suggesting optimal meeting points for groups
Neighborhood exploration and data aggregation
Locating educational institutions and schools
Commute route analysis
EV charging station lookup with detailed filtering
Parking facility search with availability and fee details

Use Cases

Finding optimal meeting points for multiple users
Analyzing neighborhood features for real estate evaluation
Searching for nearby restaurants, schools, or facilities
Providing LLM-based parking search with real-time info
Generating directions between multiple locations
Locating EV charging stations by connector type or power
Comparing commute options between home and work
Reverse geocoding to get addresses for map pins
Exploring neighborhood livability for property search
Assisting location-aware language model applications

README

OpenStreetMap (OSM) MCP Server

An OpenStreetMap MCP server implementation that enhances LLM capabilities with location-based services and geospatial data.

Demo

Meeting Point Optimization

Meeting Point Use Case

Neighborhood Analysis

Neighborhood Analysis Use Case

Parking Search

Parking Search Use Case

Installation

In MCP Hosts like Claude Desktop, Cursor, Windsurf, etc.

  • osm-mcp-server: The main server, available for public use.

    json
    "mcpServers": {
  "osm-mcp-server": {
    "command": "uvx",
    "args": [
      "osm-mcp-server"
    ]
  }
}

Features

This server provides LLMs with tools to interact with OpenStreetMap data, enabling location-based applications to:

  • Geocode addresses and place names to coordinates
  • Reverse geocode coordinates to addresses
  • Find nearby points of interest
  • Get route directions between locations
  • Search for places by category within a bounding box
  • Suggest optimal meeting points for multiple people
  • Explore areas and get comprehensive location information
  • Find schools and educational institutions near a location
  • Analyze commute options between home and work
  • Locate EV charging stations with connector and power filtering
  • Perform neighborhood livability analysis for real estate
  • Find parking facilities with availability and fee information

Components

Resources

The server implements location-based resources:

  • location://place/{query}: Get information about places by name or address
  • location://map/{style}/{z}/{x}/{y}: Get styled map tiles at specified coordinates

Tools

The server implements several geospatial tools:

  • geocode_address: Convert text to geographic coordinates
  • reverse_geocode: Convert coordinates to human-readable addresses
  • find_nearby_places: Discover points of interest near a location
  • get_route_directions: Get turn-by-turn directions between locations
  • search_category: Find places of specific categories in an area
  • suggest_meeting_point: Find optimal meeting spots for multiple people
  • explore_area: Get comprehensive data about a neighborhood
  • find_schools_nearby: Locate educational institutions near a specific location
  • analyze_commute: Compare transportation options between home and work
  • find_ev_charging_stations: Locate EV charging infrastructure with filtering
  • analyze_neighborhood: Evaluate neighborhood livability for real estate
  • find_parking_facilities: Locate parking options near a destination

Local Testing

Running the Server

To run the server locally:

  1. Install the package in development mode:
bash
pip install -e .
  1. Start the server:
bash
osm-mcp-server
  1. The server will start and listen for MCP requests on the standard input/output.

Testing with Example Clients

The repository includes two example clients in the examples/ directory:

Basic Client Example

client.py demonstrates basic usage of the OSM MCP server:

bash
python examples/client.py

This will:

  • Connect to the locally running server
  • Get information about San Francisco
  • Search for restaurants in the area
  • Retrieve comprehensive map data with progress tracking

LLM Integration Example

llm_client.py provides a helper class designed for LLM integration:

bash
python examples/llm_client.py

This example shows how an LLM can use the Location Assistant to:

  • Get location information from text queries
  • Find nearby points of interest
  • Get directions between locations
  • Find optimal meeting points
  • Explore neighborhoods

Writing Your Own Client

To create your own client:

  1. Import the MCP client:
python
from mcp.client import Client
  1. Initialize the client with your server URL:
python
client = Client("http://localhost:8000")
  1. Invoke tools or access resources:
python
# Example: Geocode an address
results = await client.invoke_tool("geocode_address", {"address": "New York City"})

Claude Desktop config for local server

On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json

json
"mcpServers": {
  "osm-mcp-server": {
    "command": "uv",
    "args": [
      "--directory",
      "/path/to/osm-mcp-server",
      "run",
      "osm-mcp-server"
    ]
  }
}

Development

Building and Publishing

To prepare the package for distribution:

  1. Sync dependencies and update lockfile:
bash
uv sync
  1. Build package distributions:
bash
uv build

This will create source and wheel distributions in the dist/ directory.

  1. Publish to PyPI:
bash
uv publish

Note: You'll need to set PyPI credentials via environment variables or command flags.

Debugging

Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.

You can launch the MCP Inspector via npm with this command:

bash
npx @modelcontextprotocol/inspector uv --directory /path/to/osm-mcp-server run osm-mcp-server

Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.

Star History

Star History Chart

Repository Owner

jagan-shanmugam

Repository Details

Language Python
Default Branch main
Size 58,740 KB
Contributors 2
License MIT License
MCP Verified Nov 12, 2025

Programming Languages

Python
100%

Tags

Location Services llm-integration

Topics

anthropic-claude llm mcp mcp-server openstreetmap

Join Our Newsletter

Stay updated with the latest AI tools, news, and offers by subscribing to our weekly newsletter.

We respect your privacy. Unsubscribe at any time.

Related MCPs

Discover similar Model Context Protocol servers

  • MCP-Geo

    MCP-Geo

    Geocoding and reverse geocoding MCP server for LLMs.

    MCP-Geo provides geocoding and reverse geocoding capabilities to AI models using the Model Context Protocol, powered by the GeoPY library. It offers various tools such as address lookup, reverse lookup from coordinates, distance calculations, and batch processing of locations, all accessible via standard MCP tool interfaces. Safety features like rate limiting and robust error handling ensure reliable and compliant usage of geocoding services. The server is compatible with environments like Claude Desktop and can be easily configured elsewhere.

    • ⭐ 28
    • MCP
    • webcoderz/MCP-Geo
  • GIS MCP Server

    GIS MCP Server

    Empower AI with advanced geospatial operations via Model Context Protocol.

    GIS MCP Server provides a Model Context Protocol (MCP) server implementation that enables Large Language Models to access and perform sophisticated GIS operations. It bridges AI assistants with Python geospatial libraries such as Shapely, GeoPandas, PyProj, Rasterio, and PySAL. The server supports a wide range of spatial analysis, coordinate transformations, raster and vector data processing, and geospatial intelligence tasks. By integrating with MCP-compatible clients, it enhances AI tools with precise and extensible spatial capabilities.

    • ⭐ 70
    • MCP
    • mahdin75/gis-mcp
  • Stadia Maps MCP Server (TypeScript)

    Stadia Maps MCP Server (TypeScript)

    Bringing location services, geocoding, and mapping to AI assistants via Stadia Maps APIs.

    Stadia Maps MCP Server (TypeScript) implements the Model Context Protocol to provide LLM-based assistants with structured access to Stadia Maps APIs. It enables AI tools to query for geocoding, routing, time zones, map generation, and isochrone calculations. Designed for integration with agentic tools and LLMs, the server enhances spatial intelligence and location-based features in AI workflows.

    • ⭐ 18
    • MCP
    • stadiamaps/stadiamaps-mcp-server-ts
  • GeoServer MCP Server

    GeoServer MCP Server

    Connect LLMs to GeoServer for geospatial data management and AI-driven queries.

    GeoServer MCP Server implements the Model Context Protocol, enabling seamless integration between Large Language Models (LLMs) and the GeoServer REST API. It allows AI assistants to interact with, query, and manipulate geospatial data and services through standardized interfaces. The server supports management of workspaces, layers, and spatial queries, as well as rendering geospatial visualizations. Installation is supported via Docker, pip, and integration tools like Smithery, with compatibility for clients such as Claude Desktop and Cursor.

    • ⭐ 43
    • MCP
    • mahdin75/geoserver-mcp
  • MCP Server for Odoo

    MCP Server for Odoo

    Connect AI assistants to Odoo ERP systems using the Model Context Protocol.

    MCP Server for Odoo enables AI assistants such as Claude to interact seamlessly with Odoo ERP systems via the Model Context Protocol (MCP). It provides endpoints for searching, creating, updating, and deleting Odoo records using natural language while respecting access controls and security. The server supports integration with any Odoo instance, includes smart features like pagination and LLM-optimized output, and offers both demo and production-ready modes.

    • ⭐ 101
    • MCP
    • ivnvxd/mcp-server-odoo
  • OpenTK Model Context Protocol Server

    OpenTK Model Context Protocol Server

    A standardized interface for LLMs to access Dutch parliamentary data.

    OpenTK Model Context Protocol Server provides a bridge between large language models and Dutch parliamentary data using the Model Context Protocol (MCP). It enables AI systems to access, search, and analyze parliamentary documents, debates, and member information from the Tweede Kamer through a unified and structured interface. By leveraging the @modelcontextprotocol/sdk, it ensures consistent context management for model interactions. Built atop the OpenTK project, it delivers streamlined access to extensive open government datasets.

    • ⭐ 16
    • MCP
    • r-huijts/opentk-mcp
    • View all Alternatives

    Didn't find tool you were looking for?

    Be as detailed as possible for better results