MCP-Bridge MCP — Use Cases, Install & Live Demo

Why use it

Key features

Exposes MCP tools as OpenAI-style functions to any OpenAI-compatible client
REST + SSE endpoints; mirrors /v1/chat/completions
Multiple upstream MCP servers configured in one JSON
Optional bearer auth for the bridge itself
Runs as Docker container or uv sync Python app

Live Demo

What it looks like in practice

bridge.replay ▶ ready

0/0

Install

Pick your client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "bridge": {
      "command": "uvx",
      "args": [
        "MCP-Bridge"
      ],
      "_inferred": true
    }
  }
}

Open Claude Desktop → Settings → Developer → Edit Config. Restart after saving.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "bridge": {
      "command": "uvx",
      "args": [
        "MCP-Bridge"
      ],
      "_inferred": true
    }
  }
}

Cursor uses the same mcpServers schema as Claude Desktop. Project config wins over global.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "bridge": {
      "command": "uvx",
      "args": [
        "MCP-Bridge"
      ],
      "_inferred": true
    }
  }
}

Click the MCP Servers icon in the Cline sidebar, then "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "bridge": {
      "command": "uvx",
      "args": [
        "MCP-Bridge"
      ],
      "_inferred": true
    }
  }
}

Same shape as Claude Desktop. Restart Windsurf to pick up changes.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "bridge",
      "command": "uvx",
      "args": [
        "MCP-Bridge"
      ]
    }
  ]
}

Continue uses an array of server objects rather than a map.

~/.config/zed/settings.json

{
  "context_servers": {
    "bridge": {
      "command": {
        "path": "uvx",
        "args": [
          "MCP-Bridge"
        ]
      }
    }
  }
}

Add to context_servers. Zed hot-reloads on save.

claude mcp add bridge -- uvx MCP-Bridge

One-liner. Verify with claude mcp list. Remove with claude mcp remove.

Use Cases

Real-world ways to use MCP-Bridge

Add MCP tools to LibreChat / any OpenAI-compatible chat UI

👤 Self-hosters of OSS chat frontends ⏱ ~30 min intermediate

When to use: You're running LibreChat, Big-AGI, or a custom app that calls /v1/chat/completions and wants tool use, but it doesn't speak MCP.

Prerequisites

An OpenAI-compatible inference backend — OpenAI, Anthropic-via-proxy, vLLM, Ollama, etc.
At least one MCP server you want to expose — filesystem, fetch, postgres — whatever you've got

Flow

Write config.json

Write me an MCP-Bridge config.json that proxies OpenAI and exposes filesystem MCP (rooted at /data) and fetch MCP.✓ Copied

→ Valid config with inference_server and mcp_servers sections
Run via Docker

Give me the docker run command to start MCP-Bridge using this config on port 8000.✓ Copied

→ Working docker command with volume mounts
Point the chat UI at the bridge

Show me what API base URL to set in LibreChat to use the bridge instead of OpenAI directly.✓ Copied

→ Config pointing to http://localhost:8000/v1

Outcome: LibreChat conversations can now call filesystem and fetch tools, transparently.

Pitfalls

Not all OpenAI-compatible clients support tool calls — Verify your UI supports functions in responses before wiring; check its docs for 'tool calling' support
Streaming responses not yet implemented — Disable streaming in the client; use non-streaming endpoints

Combine with: filesystem · fetch

Give your own Python/JS agent framework MCP tool access

👤 Devs building custom agents on OpenAI SDK ⏱ ~25 min intermediate

When to use: You're building with the raw OpenAI SDK (or LangChain's OpenAI client) and want to plug in the MCP ecosystem without rewriting the agent.

Flow

Start MCP-Bridge locally

Run MCP-Bridge with upstream set to OpenAI and these MCP servers: [list].✓ Copied

→ Bridge listening on :8000
Point OpenAI client base_url at the bridge

Show me Python SDK init: client = OpenAI(base_url='http://localhost:8000/v1', api_key=...). Then call chat completions.✓ Copied

→ Code snippet that works unchanged

Outcome: Zero-touch tool access for your existing agent code.

Pitfalls

Bridge is a single point of failure — For prod, run with supervisord/systemd and healthcheck endpoint

Combinations

Pair with other MCPs for X10 leverage

bridge + filesystem + fetch

Budget self-hosted ChatGPT replacement with real tool use

Expose filesystem (rooted at ~/Notes) and fetch via MCP-Bridge, then use LibreChat to browse + summarize.✓ Copied

Tools

What this MCP exposes

Tool	Inputs	When to call	Cost
POST /v1/chat/completions	OpenAI-compatible messages + tools omitted (auto-injected)	Main entrypoint — drop-in for OpenAI	1 LLM call + N tool calls
GET /tools		Discover what's available	free
SSE /bridge		Attach an external MCP client to the bridge over SSE	free

Cost & Limits

What this costs to run

API quota: Pass-through — whatever your upstream inference provider charges
Tokens per call: Bridge adds ~100-500 tokens of tool definitions per request
Monetary: Free (MIT). You pay for your LLM + wherever you host it.
Tip: Only attach MCP servers you need — every attached tool bloats the system prompt.

Security

Permissions, secrets, blast radius

Credential storage: Upstream API key + MCP server creds in config.json; lock down file permissions

Data egress: Requests go to your configured upstream (e.g. OpenAI) + whichever MCP servers

Never grant: Expose the bridge to the internet without enabling bearer auth

Streaming not implemented — clients that require streaming will fail.
Soft-deprecated in favor of Open WebUI's native MCP (0.6.31+) if you use Open WebUI specifically.

Troubleshooting

Common errors and fixes

Client says 'tool_use not supported'

Upstream model or client UI doesn't support function calling. Use a model that does (gpt-4o, claude, llama 3.1+).

MCP server connection refused

Check the command in config.json actually runs. Bridge runs it as subprocess; test manually: npx -y the-mcp.

401 from bridge when auth enabled

Set Authorization: Bearer <key> header; the key must be in config under security.auth.keys.

Alternatives

MCP-Bridge vs others

Alternative	When to use it instead	Tradeoff
Open WebUI native MCP	You specifically use Open WebUI 0.6.31+	Built-in — no bridge needed, but Open WebUI only
LiteLLM with custom callbacks	You want multi-provider routing + tool injection	More complex; LiteLLM doesn't natively speak MCP either
mcpo	You want to expose MCP tools as plain OpenAPI for non-LLM clients too	Different shape — OpenAPI-first rather than chat-completions-first

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills