Google Stitch MCP Proxy
Proxies Google Stitch MCP endpoint, injecting the API key from environment variable for secure access.
README
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。
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。
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.