MCP cover image
See in Github
2025-04-14

0

Github Watches

0

Github Forks

0

Github Stars

Snappy MCP Server with Xano Integration

A remote MCP server built on Cloudflare Workers with Xano database integration for tool management, session tracking, and OAuth.

Develop locally

# clone the repository
git clone https://github.com/roboulos/remote-mcp-server.git

# install dependencies
cd remote-mcp-server
npm install

# Configure Xano API Key
# Add your Xano API key to wrangler.jsonc in the XANO_API_KEY variable

# run locally
npm run dev

You should be able to open http://localhost:8787/ in your browser

Connect the MCP inspector to your server

To explore your new MCP api, you can use the MCP Inspector.

  • Start it with npx @modelcontextprotocol/inspector
  • Within the inspector, switch the Transport Type to SSE and enter http://localhost:8787/sse as the URL of the MCP server to connect to, and click "Connect"
  • You will navigate to a (mock) user/password login screen. Input any email and pass to login.
  • You should be redirected back to the MCP Inspector and you can now list and call any defined tools!
remote-mcp-server img/mcp-inspector-sse-config.png
remote-mcp-server img/mcp-inspector-successful-tool-call.png

Connect Claude Desktop to your local MCP server

The MCP inspector is great, but we really want to connect this to Claude! Follow Anthropic's Quickstart and within Claude Desktop go to Settings > Developer > Edit Config to find your configuration file.

Open the file in your text editor and replace it with this configuration:

{
  "mcpServers": {
    "math": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "http://localhost:8787/sse"
      ]
    }
  }
}

This will run a local proxy and let Claude talk to your MCP server over HTTP

When you open Claude a browser window should open and allow you to login. You should see the tools available in the bottom right. Given the right prompt Claude should ask to call the tool.

remote-mcp-server img/available-tools.png
remote-mcp-server img/claude-does-math-the-fancy-way.png

Xano Integration

This MCP server uses Xano as its backend for:

  1. Tool Management: Define tools in Xano's ____mcp_tools table and they will be automatically registered in the MCP server
  2. Session Tracking: All MCP sessions are tracked in the ___mcp_sessions table
  3. OAuth Authentication: OAuth tokens and states are stored in Xano's ___oauth_tokens and ___oauth_states tables
  4. Logging: All MCP requests are logged in the ___mcp_logs table

Setting up Xano

  1. Create a Xano project with the required tables (see database schema)
  2. Create API endpoints for:
    • /api/tools - GET - List all tools
    • /api/tools/execute/{tool_name} - POST - Execute a specific tool
    • /api/sessions - POST - Create a new session
    • /api/sessions/update-activity - PUT - Update session activity
    • /api/oauth/tokens - POST - Store OAuth tokens
    • /api/oauth/tokens/{user_id}/{provider} - GET - Get OAuth tokens
    • /api/oauth/states - POST - Store OAuth states
    • /api/oauth/states/{state} - GET - Validate OAuth states
    • /api/logs - POST - Log MCP requests

Deploy to Cloudflare

  1. npx wrangler kv namespace create OAUTH_KV
  2. Follow the guidance to add the kv namespace ID to wrangler.jsonc
  3. Add your Xano API key to the XANO_API_KEY variable in wrangler.jsonc
  4. npm run deploy

Call your newly deployed remote MCP server from a remote MCP client

Just like you did above in "Develop locally", run the MCP inspector:

npx @modelcontextprotocol/inspector@latest

Then enter the workers.dev URL (ex: worker-name.account-name.workers.dev/sse) of your Worker in the inspector as the URL of the MCP server to connect to, and click "Connect".

You've now connected to your MCP server from a remote MCP client.

Connect Claude Desktop to your remote MCP server

Update the Claude configuration file to point to your workers.dev URL (ex: worker-name.account-name.workers.dev/sse) and restart Claude

{
  "mcpServers": {
    "math": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://worker-name.account-name.workers.dev/sse"
      ]
    }
  }
}

Debugging

Should anything go wrong it can be helpful to restart Claude, or to try connecting directly to your MCP server on the command line with the following command.

npx mcp-remote http://localhost:8787/sse

In some rare cases it may help to clear the files added to ~/.mcp-auth

rm -rf ~/.mcp-auth

相关推荐

  • Aurity Ltd
  • Create and Publish Business Websites in seconds. AI will gather all the details about your website and generate link to your website.

  • Convincible Ltd
  • You're in a stone cell – can you get out? A classic choose-your-adventure interactive fiction game, based on a meticulously-crafted playbook. With a medieval fantasy setting, infinite choices and outcomes, and dice!

  • John Rafferty
  • Text your favorite pet, after answering 10 questions about their everyday lives!

  • Ian O'Connell
  • Provide players' names or enter Quickstart to start the game!

  • analogchat.com
  • Efficient Spotify assistant for personalized music data.

  • Matthieu Savioux
  • Evaluates language quality of texts, responds with a numerical score between 50-150.

  • seabiscuit.ai
  • Discover A More Robust Business: Craft tailored value proposition statements, develop a comprehensive business model canvas, conduct detailed PESTLE analysis, and gain strategic insights on enhancing business model elements like scalability, cost structure, and market competition strategies. (v1.18)

  • WangRongsheng
  • 🧑‍🚀 全世界最好的LLM资料总结(Agent框架、辅助编程、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型) | Summary of the world's best LLM resources.

  • n8n-io
  • Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

  • av
  • Effortlessly run LLM backends, APIs, frontends, and services with one command.

  • metorial
  • Containerized versions of hundreds of MCP servers 📡 🧠

  • langgenius
  • Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.

  • Azure
  • The Azure MCP Server, bringing the power of Azure to your agents.

  • alibaba
  • an easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.

  • 1Panel-dev
  • 🔥 1Panel provides an intuitive web interface and MCP Server to manage websites, files, containers, databases, and LLMs on a Linux server.

  • caio-moliveira
  • This project was created to demonstrate how we can connect with different Model Context Protocols (MCPs).

  • superiorlu
  • 🤖 Collect practical AI repos, tools, websites, papers and tutorials on AI. 实用的AI百宝箱 💎

  • rulego
  • ⛓️RuleGo is a lightweight, high-performance, embedded, next-generation component orchestration rule engine framework for Go.

  • Byaidu
  • PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译,支持 Google/DeepL/Ollama/OpenAI 等服务,提供 CLI/GUI/MCP/Docker/Zotero

    Reviews

    2 (1)
    Avatar
    user_5LjBUlhP
    2025-04-23

    I've been using the remote-mcp-server by roboulos and it's been a game-changer for my workflow. The setup is straightforward, and its performance is rock-solid. It handles remote operations seamlessly, significantly improving my productivity. Highly recommend it to anyone in need of a reliable remote server solution.