MCP Bridge API
@INQUIRELAB
MCP Bridge API について
MCP Bridge is a lightweight, fast, and LLM-agnostic proxy for connecting to multiple Model Context Protocol (MCP) servers through a unified REST API. It enables secure tool execution across diverse environments like mobile, web, and edge devices. Designed for flexibility, scalabi
基本情報
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"mcp-bridge-api": {
"command": "node",
"args": [
"mcp-bridge.js"
]
}
}
}ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is MCP Bridge API?
MCP Bridge API is a lightweight, LLM-agnostic RESTful proxy that connects to multiple Model Context Protocol (MCP) servers and exposes their capabilities through a unified REST API. It enables any client on any platform to leverage MCP functionality without requiring local process execution, and includes optional risk-based execution levels for granular security control.
How to use MCP Bridge API?
Install Node.js 18+, then run npm install express cors morgan uuid and node mcp-bridge.js. Configure MCP servers by editing mcp_config.json in the project root. The server exposes REST endpoints at /health, /servers, and per‑server tool, resource, and prompt endpoints. Two client implementations are provided: a Python command‑line agent and a React Native mobile app.
Key features of MCP Bridge API
- LLM-agnostic RESTful proxy for MCP servers
- Supports multiple MCP servers simultaneously
- Optional risk-based security levels (standard, confirmation, Docker isolation)
- Compatible with any client on any platform
- Automatically exposes all MCP tools via REST API
Use cases of MCP Bridge API
- Enable mobile apps to access MCP tools without local process execution
- Provide a web frontend with unified access to multiple
「開発者ツール」の他のコンテンツ
test
prysmaticlabsGo implementation of Ethereum proof of stake
MCP-Bridge
SecretiveShellA middleware to provide an openAI compatible endpoint that can call MCP tools
nuxt-mcp / vite-plugin-mcp
antfuMCP server helping models to understand your Vite/Nuxt app better.
MCP Containers
metorialConnect any AI model to 1200+ integrations (MCP, CLI, API)
Golf
golf-mcpProduction-Ready MCP Server Framework • Build, deploy & scale secure AI agent infrastructure • Includes Auth, Observability, Debugger, Telemetry & Runtime • Run real-world MCPs powering AI Agents
コメント