MCP-connect
by EvalsOne
Overview
A lightweight bridge service that exposes local MCP servers as HTTP APIs, enabling cloud AI tools and agents to interact with various local MCP services via Streamable HTTP or a classic request/response bridge.
Installation
npm startEnvironment Variables
- AUTH_TOKEN
- ACCESS_TOKEN
- PORT
- HOST
- LOG_LEVEL
- ALLOWED_ORIGINS
- NGROK_AUTH_TOKEN
- STREAM_SESSION_TTL_MS
- DISABLE_BRIDGE_CLEANUP
- MCP_SERVERS
- NPM_CI_ALWAYS
- E2B_API_KEY
- E2B_TEMPLATE_ID
- E2B_SANDBOX_TIMEOUT
- E2B_MCP_AUTH_TOKEN
- XVFB_RESOLUTION
- X11VNC_WAIT
- X11VNC_DEFER
- X11VNC_COMPRESSION
- X11VNC_QUALITY
- X11VNC_EXTRA
- N8N_API_URL
- N8N_API_KEY
Security Notes
CRITICAL VULNERABILITIES: The `/bridge` endpoint allows an unauthenticated or authenticated client to specify an arbitrary `serverPath` in the request body. If this `serverPath` is a command (e.g., `rm -rf /`), the `MCPClientManager` will directly execute it via `StdioClientTransport`. This is a direct command injection vulnerability. Additionally, the `AUTH_TOKEN` environment variable defaults to an empty string, meaning the server runs unauthenticated by default. This allows any client to make calls, including exploiting the command injection. The `deploy/e2b/sandbox_deploy.py` script also fetches `startup.sh` and other configuration from a `remote_base` URL by default, which introduces a supply chain risk if the remote source is compromised. Sensitive environment variables like `N8N_API_KEY` can be included in `mcp-servers.json` and are handled via environment variable resolution, requiring careful management to prevent leaks.
Similar Servers
klavis
Creates an AI agent capable of interacting with multiple applications (like Gmail and YouTube in the example) by routing tool calls through a unified Model Context Protocol (MCP) server (Strata), providing off-the-shelf intelligent connectors for AI agents.
mcpo
Exposes Model Context Protocol (MCP) tools as OpenAPI-compatible HTTP servers.
mcp-context-forge
An MCP server for retrieving web content and files, then converting them to high-quality markdown format.
mcphub
A centralized hub for managing, orchestrating, and exposing Model Context Protocol (MCP) servers and their tools/prompts, including OAuth authorization, user/group management, and dynamic registration of clients.