
远程MCP-Server
3 years
Works with Finder
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 enterhttp://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!


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.


Xano Integration
This MCP server uses Xano as its backend for:
-
Tool Management: Define tools in Xano's
____mcp_tools
table and they will be automatically registered in the MCP server -
Session Tracking: All MCP sessions are tracked in the
___mcp_sessions
table -
OAuth Authentication: OAuth tokens and states are stored in Xano's
___oauth_tokens
and___oauth_states
tables -
Logging: All MCP requests are logged in the
___mcp_logs
table
Setting up Xano
- Create a Xano project with the required tables (see database schema)
- 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
-
npx wrangler kv namespace create OAUTH_KV
- Follow the guidance to add the kv namespace ID to
wrangler.jsonc
- Add your Xano API key to the
XANO_API_KEY
variable inwrangler.jsonc
-
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
Flock是一个基于工作流程的低音平台,可快速构建聊天机器人,抹布和协调多代理团队,由Langgraph,Langchain,Langchain,Fastapi和Nextjs提供支持。(羊群工作流工作流的低代码平台,rag rag rag 用于快速构建聊天机器人、 rag temant Agent fastem temantfaster和muti-agent agagent应用
😎简单易用、🧩丰富生态 -大模型原生即时通信机器人平台| 适配QQ / 微信(企业微信、个人微信) /飞书 /钉钉 / discord / telegram / slack等平台| 支持chatgpt,deepseek,dify,claude,基于LLM的即时消息机器人平台,支持Discord,Telegram,微信,Lark,Dingtalk,QQ,Slack
Reviews

user_5LjBUlhP
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.