tripgo
MCP server for TripGo's multi-modal routing
claude mcp add --transport stdio skedgo-tripgo-mcp-server npx mcp-remote https://tripgo-mcp-server.skedgo-account.workers.dev/mcp
How to use
TripGo MCP Server exposes several tools that wrap the TripGo API and present them via the MCP protocol. The available tools are: tripgo-locations for retrieving transport-related locations, tripgo-departures to get departures from a specific public transport stop, tripgo-routing for mixed- and multi-modal trip planning, and tripgo-get-trip-url to fetch the URL of a trip previously calculated with tripgo-routing. The server itself is deployed as a Cloudflare Worker and is reachable at https://tripgo-mcp-server.skedgo-account.workers.dev/mcp. To use these tools from a local MCP client (for example Claude Desktop), connect through the mcp-remote proxy by pointing to the remote MCP endpoint. The README provides concrete example configurations for connecting via Claude Desktop and demonstrates how to initialize the remote server in Claude’s settings. Once connected, Claude will expose the available tools under the configured server name (e.g., TripGo) so you can invoke tripgo-locations, tripgo-departures, tripgo-routing, and tripgo-get-trip-url inside your workspace.
How to install
Prerequisites: Node.js and npm installed on your machine; a path to run MCP clients (e.g., Claude Desktop) that supports the MCP protocol. Steps:\n1) Install dependencies for the MCP client ecosystem (example shown uses npm).\n2) Install and run the remote MCP proxy client to connect to the TripGo MCP server:\n\n npm install ``\n\n
To connect Claude Desktop to the remote TripGo MCP server:\n```
Example within Claude configuration (as shown in the README):
{ "mcpServers": { "TripGo": { "command": "npx", "args": [ "mcp-remote", "https://tripgo-mcp-server.skedgo-account.workers.dev/mcp" ] } } }
3) Restart Claude Desktop to load the new MCP server configuration and enable the TripGo tools. If you want to run a local development workflow (as shown in the README for a local Claude setup), you can replicate the local deployment steps: install dependencies and run the local deploy script using npm, then point the remote proxy to http://localhost:8787/mcp for testing locally.
Additional notes
Notes and tips:\n- The TripGo MCP server is hosted as a Cloudflare Worker; the public endpoint is the primary access point. If you are configuring Claude Desktop, ensure the mcp-remote proxy is accessible from your network.\n- The example configurations use the server name TripGo; you can rename it to anything suitable for your workspace (e.g., TripGo).\n- If you encounter authentication or API key issues, follow the .env setup steps as described in Development (copy .env.example to .env and place your TripGo API key there).\n- When testing locally, the README shows an alternative local configuration pointing Claude to http://localhost:8787/mcp. Ensure port 8787 is available and the local dev server is running.\n- If you switch environments (remote vs. local), keep the same tool names to minimize changes in your Claude workflows.
Related MCP Servers
context7
Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
obsidian -tools
Add Obsidian integrations like semantic search and custom Templater prompts to Claude or any MCP client.
MiniMax -JS
Official MiniMax Model Context Protocol (MCP) JavaScript implementation that provides seamless integration with MiniMax's powerful AI capabilities including image generation, video generation, text-to-speech, and voice cloning APIs.
mcp-bundler
Is the MCP configuration too complicated? You can easily share your own simplified setup!
akyn-sdk
Turn any data source into an MCP server in 5 minutes. Build AI-agents-ready knowledge bases.
promptboard
The Shared Whiteboard for Your AI Agents via MCP. Paste screenshots, mark them up, and share with AI.