Integration · MODEL CONTEXT PROTOCOL
huanshenyi mcp server bearer auth
huanshenyi mcp server bearer auth is a community-listed Model Context Protocol server. Review the source repository before installation.
连接能力
huanshenyi mcp server bearer auth 为 AI Agent 提供什么
来源目录未提供结构化功能列表,请在使用前阅读源仓库文档。
安全
MCP 收录不等于安全审核
MCP 服务器可能获得模型上下文、凭据、本地文件或调用外部系统的权限。连接 Agent 前,请检查代码、环境变量、网络行为、软件包来源与维护状态。
README
仓库文档
Let's get a remote MCP server up-and-running on Cloudflare Workers complete with OAuth login!
# clone the repository
git clone git@github.com:cloudflare/ai.git
# install dependencies
cd ai
npm install
# run locally
npx nx dev remote-mcp-server-bearer-authYou should be able to open http://localhost:8787/ in your browser
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
SSEand enterhttp://localhost:8787/sseas the URL of the MCP server to connect to. - Add a bearer token and click "Connect"
- Click "List Tools"
- Run the "getToken" tool, which should return the Authorization header that you set in the inspector
"remote-example": {
"command": "npx",
"args": [
"mcp-remote",
"http://localhost:8787/sse",
"--header",
"Authorization: Bearer {token}"
]
}npm run deploy
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. You can pass in a bearer token like mentioned above
TODO: We need to support arbitrary headers to the mcp-remote proxy
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/sseIn some rare cases it may help to clear the files added to ~/.mcp-auth
rm -rf ~/.mcp-auth社区

