MCP Gateway
A compact non-production-ready MCP gateway that routes tool calls to configured downstream MCP servers, with a dashboard to enable or disable tools.
README
MCP Gateway

A compact non-production-ready MCP gateway.
Built with LLM-powered tools to befriend LLMs and the tools.
Use cases
- You need to expose the MCP server beyond localhost (ie for a dockerized harness)
- You want to use the MCP server, but disable some of its tools
- You need to expose the MCP, using one protocol, to a harness using other protocol
It routes (proxies) tool calls to configured downstream MCP servers.
It currently supports downstream streamable-http and sse transports.
It also has a dashboard where you can enable or disable certain tools.
Run
uv sync
cp gateway.example.json gateway.json
uv run mcp-gateway
Use the MCP Inspector or any MCP client against /http/mcp (or /sse/sse for a legacy client).
Configure upstream clients
Add http://localhost:64345/http/mcp as an endpoint to your client or harness.
Configure downstream servers
Edit gateway.json accordingly.
headers are optional and are never shown by the dashboard.
disabled_tools is optional per server. List downstream tool names (before any gateway renaming) to hide at startup.
Restart the gateway after changing this list.
Exposed tools
The gateway exposes only tools discovered from downstream servers. It copies each tool's name, description, schemas, annotations, and result without a gateway wrapper.
When two or more downstream servers expose the same tool name, every conflicting tool is exposed as
servername-toolname, for example github-search.
Tool discovery happens at gateway startup. Restart the gateway to pick up downstream inventory changes.
Disclaimer
This is a starter gateway, not an authorization boundary. Expect bugs. Never expose beyond localhost.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。