Ola Maps MCP Server

Ola Maps MCP Server provides seamless integration with MCP clients like Claude, Cursor, and Windsurf, enabling users to interact with Ola Maps services effortlessly. Currently, the server supports a range of powerful location-based services, including geocoding and reverse geocoding for address and coordinate conversion, elevation retrieval, detailed place information lookup, and nearby search for points of interest. Additionally, users can fetch optimized routes between locations and calculate travel distances for multiple origin-destination pairs via the distance matrix API. Looking ahead, we plan to enhance the server with more advanced routing capabilities, real-time traffic, and map-tiles insights, making Ola Maps MCP a more comprehensive solution for location-based intelligence.
Our platform provides robust B2B map services, and the Ola Maps MCP Server is the next leap forward, specifically designed to empower applications interacting with LLMs. It provides the crucial location context these models need to perform tasks related to the physical world with unprecedented accuracy.
We have also published a reference of ola-maps-mcp-server on the official MCP GitHub. Check it outhere.

Features

  • get_geocode: Provides probable geographic coordinates and detailed location information including a formatted address for the given address as input.
  • reverse_geocode: Converts geographic coordinates back into readable addresses or place names.
  • get_elevation: Retrieves elevation data for a single location.
  • get_placeDetails: Provides place details of a particular Place/POI whose Ola place_id necessarily needs to be given as an input.
  • nearbysearch: Provides nearby places of a particular category/type based on the given location.
  • textsearch: Provides a list of places based on textual search without needing actual location coordinates.
  • get_directions: Provides a routable path between two places.
  • distancematrix: Calculates travel distance between multiple origins and destinations.

Configuring mcp-ola-maps server with Claude

Prerequisites : Need to have claude desktop application, python>=3.10 and uvx installed on the machine. To install python visithere. To Install uvx visithere. To Install Claude Desktop Application visithere. Along with these prerequisites, you need to have an Ola Maps API key. To get the API key, Follow the instructionshere.
Step 1: Open the Claude Desktop configuration file:
  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%/Claude/claude_desktop_config.json
Step 2: Add the following configuration:
{
  "mcpServers": {
    "mcp-ola-maps": {
      "command": "uvx",
      "args": ["ola-maps-mcp-server"],
      "env": {
        "OLA_MAPS_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}
Step 3: Ensure the correct uvx executable path:
which uvx
Replace "command": "uvx" with the absolute path to uvx, if necessary.
Step 4: Restart Claude Desktop to apply the changes.

Integration for Client Developers

Refer to theofficial MCP documentationto start with writing your own basic client. To integrate Ola Maps MCP Server, you need to modify the server connection management code, specifically the StdioServerParameters function call.
Server Connection Management :
We'll make the below changes in the method to connect to Ola Maps MCP server:
async def connect_to_server(self):
    """
    Connect to Ola Maps MCP server
    """
    # Modify the code as below to integrate ola-maps-mcp-server
    server_params = StdioServerParameters(
        command="uvx",
        args=["ola-maps-mcp-server"],
        env={
            "OLA_MAPS_API_KEY": "YOUR_OLA_MAPS_API_KEY"
        }
    )

    stdio_transport = await self.exit_stack.enter_async_context(stdio_client(server_params))
    self.stdio, self.write = stdio_transport
    self.session = await self.exit_stack.enter_async_context(ClientSession(self.stdio, self.write))

    await self.session.initialize()

    # List available tools
    response = await self.session.list_tools()
    tools = response.tools
    print("Connected to server with tools:", [tool.name for tool in tools])
To learn more about mcp and implementation, do checkout mcp official documentationhere.