How does MCP Link differ from manually creating MCP interfaces?
MCP Link automates the conversion process from OpenAPI schemas, ensuring full functionality mapping without time‑consuming and error‑prone manual implementation.
@automation-ai-labs
基本信息
Convert Any OpenAPI V3 API to MCP Server
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"@service-name": {
"type": "http",
"url": "http://localhost:8080/sse?s=[OpenAPI-Spec-URL]&u=[API-Base-URL]&h=[Auth-Header]:[Value-Prefix]"
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,直接连接服务器端点实时获取工具列表。
MCP Link automatically converts any OpenAPI V3 API into an MCP (Model Context Protocol) server. It is designed for developers who want to make existing RESTful APIs immediately compatible with AI Agent calling standards without modifying the original API.
Clone the repository, install Go dependencies with go mod download, and run the server via go run main.go serve --port 8080 --host 0.0.0.0. Use query parameters to configure conversion: s= for the OpenAPI spec URL, u= for the API base URL, h= for authentication header format, and f= for path filter expressions. A hosted version is available at mcp-link.vercel.app for quick testing.
MCP Link automates the conversion process from OpenAPI schemas, ensuring full functionality mapping without time‑consuming and error‑prone manual implementation.
The server requires Go and its dependencies (downloaded via `go mod download`). No changes to the original API are needed.
You can run it locally on the specified port and host, or use the hosted version at mcp-link.vercel.app without any installation.
The server uses SSE (Server‑Sent Events); MCP client configuration points to an `sse` endpoint.
Authentication is configured via the `h=` parameter in the format `header-name:value-prefix`. Examples include API keys, Bearer tokens, and custom headers.
MCP server that lets Claude Code, Cursor or Codex ask you for API keys on a local page and write them to .env. The agent only ever sees key names.

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

Collide is the multiplayer layer for AI coding agents, and it pays for itself. Expert orchestration across every agent on your repo saves teams tens to hundreds of dollars a day in token burn. Run Claude Code, Codex, Cu

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation

Agent-Native Terminal
评论