drio
Open app

MCP Bridge

Source

Enables cloud-based AI services to access local Stdio based MCP servers

Catalog onlyCatalog onlySTDIO

Overview

MCP Bridge is a tool designed to enable cloud-based AI services to access local Stdio-based Model Context Protocol (MCP) servers, facilitating better interaction between cloud applications and local resources.

To use MCP Bridge, clone the repository from GitHub, set up your environment variables, install dependencies, and run the bridge. You can utilize it with or without a tunnel based on your local setup requirements.

  • Cloud Integration: Seamlessly connects cloud AI services with local MCP servers. - Protocol Translation: Converts HTTP/HTTPS requests to Stdio communication for compatibility. - Security: Ensures secure access to local resources without compromising control. - Flexibility: Supports various MCP servers with no modifications required. - Easy to use: Simple setup process with minimal configuration.
  1. Connecting cloud applications to local MCP servers for data processing.
  2. Bridging AI tools with local computational resources for enhanced performance.
  3. Running development and testing environments securely for AI models in the cloud.

Add to your AI client

Use these steps to connect MCP Bridge in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "mcp-bridge-evalsone": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-bridge-evalsone"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "mcp-bridge-evalsone": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-bridge-evalsone"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "mcp-bridge-evalsone": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-bridge-evalsone"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "mcp-bridge-evalsone": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-bridge-evalsone"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp-bridge-evalsone": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-bridge-evalsone"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "mcp-bridge-evalsone": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-bridge-evalsone"
      ]
    }
  }
}

FAQ

**What is required to set up MCP Bridge?**

You need Node.js and an MCP server to get started.

**Does MCP Bridge require any modifications to the local MCP server?**

No, it works with existing MCP server implementations without any changes.

**How can I secure my MCP Bridge setup?**

It uses a token-based authentication system which can be configured in the environment variables.7:["$","div",null,{"className":"container mx-auto flex flex-col gap-4","children":["$L26","$L27",["$","$L28",null,{"currentProject":{"id":505,"uuid":"84925491-3e69-4e03-83cd-151b464d6288","name":"MCP-bridge","title":"MCP Bridge","description":"Enables cloud-based AI services to access local Stdio based MCP servers","avatar_url":"https://avatars.githubusercontent.com/u/157576929?v=4","created_at":"2024-12-30T02:52:12.378Z","updated_at":"2025-01-05T03:00:05.152Z","status":"created","author_name":"EvalsOne","author_avatar_url":"https://avatars.githubusercontent.com/u/157576929?v=4","tags":"mcp,cloud-integration,stdio","category":"research-and-data","is_featured":false,"sort":1,"url":"https://github.com/EvalsOne/MCP-bridge","target":"_self","content":"$29","summary":"$2a","img_url":"https://camo.githubusercontent.com/6cd0120cc4c5ac11d28b2c60f76033b52db98dac641de3b2644bb054b449d60c/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f4c6963656e73652d4d49542d79656c6c6f772e737667","type":null,"metadata":null,"user_uuid":null,"tools":null,"sse_url":null,"sse_provider":null,"sse_params":null,"is_official":false,"server_command":null,"server_params":null,"server_config":null,"allow_call":false,"is_innovation":false,"is_dxt":false,"dxt_manifest":null,"dxt_file_url":null,"is_audit":false},"randomProjects":[],"currentServerKey":"$undefined"}]]}]

Research and data