Skip to main content
Glama
Vilnius Transport MCP Server

Vilnius Transport MCP Server

Vilnius Transport MCP Server

A Model Context Protocol (MCP) server implementation that provides Vilnius public transport data access capabilities to Large Language Models (LLMs). This project demonstrates how to extend LLM capabilities with real-time transport data using the MCP standard.

The Model Context Protocol (MCP) is a standard that enables Large Language Models (LLMs) to securely access external tools and data. MCP allows LLMs to:

  • Access real-time or local data

  • Call external functions claude_desktop_config.json

  • Interact with system resources

  • Maintain consistent tool interfaces

This project implements an MCP server that provides Vilnius public transport data tools to LLMs, enabling them to answer queries about public transport stops and routes.

The server exposes the following MCP tools:

  • find_stops: Search for public transport stops by name

    {
      name: string;  // Full or partial name of the stop to search for
    }
  • find_closest_stop: Find the closest public transport stop to given coordinates

    { 
      coordinates: string;  // Format: "latitude, longitude" (e.g., "54.687157, 25.279652")
    }

To add the MCP server to your Claude development environment, add the following configuration to your claude_desktop_config.json file:

   {
    "mcpServers": {
      "vilnius_transport": {
        "command": "uv",
        "args": [
            "--directory",
            "path/vilnius-transport-mcp-server/src/vilnius_transport_mcp",
            "run",
            "transport.py"
        ]
      }
    }
   }

Note: Make sure to adjust the directory path to match your local installation.

To run the client:

uv run client.py path/src/vilnius_transport_mcp/transport.py

Available Tools

2 tools
find_closest_stopC

Find the closest public transport stop to given coordinates

Inputs: coordinates (required).

find_stopsB

Search for public transport stops by name

Inputs: name (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.1/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools have clearly distinct purposes: find_closest_stop locates the nearest stop based on coordinates, while find_stops searches by name. There is no overlap in functionality, making it easy for an agent to choose the right tool for each scenario.

    Naming Consistency5/5

    Both tools follow a consistent verb_noun naming pattern (find_closest_stop, find_stops) with the same verb 'find'. The naming is predictable and readable, showing no deviations in style or convention.

    Tool Count2/5

    With only two tools, the server feels thin for a public transport domain. While the tools cover basic stop lookup, there are likely missing operations such as route planning, schedule retrieval, or real-time arrivals, which are common in transport systems. The count is too low for the apparent scope.

    Completeness2/5

    The tool surface is significantly incomplete for a transport server. It lacks core functionalities like getting routes, schedules, or vehicle positions, which are essential for comprehensive transport queries. Agents will face dead ends when trying to perform common tasks beyond stop lookup.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      A Model Context Protocol server that provides real-time access to Hong Kong's KMB and Long Win Bus route information and arrival times, enabling Language Models to answer user questions about bus routes, stops, and ETAs.
      5
      4
      Apache 2.0
    • A
      license
      Not graded
      quality
      D
      maintenance
      Provides real-time access to İzmir's public transportation data, including bus locations, schedules, and route information for ESHOT, İZBAN, Metro, and Tram services. It enables AI assistants to perform transit queries, calculate fares, and locate nearby stations using the Model Context Protocol.
      30 npm
      1
      ISC
    • A
      license
      A
      quality
      D
      maintenance
      An MCP server exposing Greater Helsinki public transport data from Digitransit, enabling LLM hosts to answer live transit queries, plan journeys, and fetch stop departures via natural language.
      3
      6 npm
      MIT