Google Stitch MCP Proxy
Proxies requests to the Google Stitch MCP API, forwarding tools, resources, prompts, and tool calls.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Google Stitch MCP ProxyWhat are the latest tech news?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Google Stitch MCP Proxy
这是一个用于 Prefect Horizon 的单一 FastMCP 项目。它把 Google Stitch 的远程 MCP:
https://stitch.googleapis.com/mcp代理为 Horizon 生成的单一 Streamable HTTP MCP 地址:
https://<server-name>.fastmcp.app/mcp连接代理的客户端不需要再提供 X-Goog-Api-Key。代理会从服务器环境变量读取密钥,并在请求上游 Stitch MCP 时注入该请求头。
安全设计
真实密钥不会写入源码或 .env.example。部署环境必须提供:
GOOGLE_API_KEY=<your-google-stitch-api-key>请把它配置为 Horizon 部署环境中的 Secret/环境变量,不要提交到 GitHub。由于代理 URL 的使用者会间接消耗这把 Google API Key,部署时建议启用 Horizon Authentication,不要把未鉴权地址公开传播。
Related MCP server: Stitch-MCP
Horizon 配置
如果仓库根目录就是本目录:
Entrypoint: main.py:mcp如果把本目录保留为主仓库中的子目录,则 Entrypoint 使用:
stitch-mcp-proxy/main.py:mcp依赖由 requirements.txt 自动检测。部署完成后的客户端连接地址为:
https://<server-name>.fastmcp.app/mcp本地运行(可选)
先在当前终端设置环境变量,然后运行:
$env:GOOGLE_API_KEY = "your-key"
fastmcp run main.py:mcp --transport http --port 8000本地端点通常是:
http://localhost:8000/mcp工作方式
ChatGPT / MCP 客户端
|
| 不携带 Google API Key
v
Horizon: /mcp
|
| X-Goog-Api-Key: 从 GOOGLE_API_KEY 注入
v
https://stitch.googleapis.com/mcp该代理会转发上游 MCP 的工具、资源、提示和工具调用,而不是重新手工实现 Stitch 工具。
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Razewang/stitch-mcp-proxy'
If you have feedback or need assistance with the MCP directory API, please join our Discord server