What runtimes are required?
Node.js 20.x or higher and npm 7.x or higher.
@vrknetha
基本信息
Bridge package enabling seamless integration between Model Context Protocol (MCP) servers and AI SDK tools. Supports multiple server types, real-time communication, and TypeScript.
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。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
A bridge package that enables seamless integration between the Model Context Protocol (MCP) and the AI SDK, allowing efficient communication and tool execution from MCP servers within AI‑powered applications. It is designed for developers who use the AI SDK and want to connect it with MCP‑compatible servers.
Install via npm install aisdk-mcp-bridge. Create an mcp.config.json file in your project root to define MCP servers, then import and call initializeMcp(), getMcpTools(), and cleanupMcp() from the package. Use the returned tool set with AI SDK functions like generateText.
mcp.config.jsonNode.js 20.x or higher and npm 7.x or higher.
Create an `mcp.config.json` file in your project root listing each server’s command, arguments, environment variables, and optional mode (stdio or SSE).
It supports stdio mode (default, direct I/O) and SSE mode (Server‑Sent Events for real‑time streaming with built‑in reconnection).
Pass the `serverName` option to `getMcpTools({ serverName: 'your-server' })`.
Set the `DEBUG` environment variable, for example `DEBUG=mcp:* npm start`, to see detailed logs on initialization, tool registration, and performance metrics.

Multi-zone MCP server for GKE/EKS/AKS: Python tools from git, NeMo guardrails, SSO, autoscaling.

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

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

Verified cyber-physical AI tools. 25 MCP tools, x402-payable on Base.

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
评论