Is MCP-Bridge still actively maintained?
MCP-Bridge is looking for new maintainers. Open WebUI natively supports MCP starting in v0.6.31, so MCP-Bridge is considered soft deprecated.
@SecretiveShell
Basic information
A middleware to provide an openAI compatible endpoint that can call MCP tools
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"MCP-Bridge": {
"command": "uv",
"args": [
"sync"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
MCP-Bridge acts as a bridge between the OpenAI API and MCP (Model Context Protocol) tools, enabling developers to leverage MCP tools through the OpenAI API interface. It is designed for developers who want to use any OpenAI-compatible client with MCP tools without requiring explicit MCP support in the client.
Recommended installation is via Docker: clone the repository, edit the compose.yml file to reference a config.json (via volume mount, HTTP URL, or environment variable), then run docker-compose up --build -d. For manual installation, clone the repo, run uv sync, create a config.json, and execute uv run mcp_bridge/main.py. Once running, interact with the OpenAI API at http://yourserver:8000/docs. Configuration requires specifying an inference_server and mcp_servers in the config file; API key authentication is optional.
mcp-cliMCP-Bridge is looking for new maintainers. Open WebUI natively supports MCP starting in v0.6.31, so MCP-Bridge is considered soft deprecated.
It requires an inference engine with tool call support (tested with vLLM; ollama is likely compatible). Docker is the recommended installation method.
Configuration is stored in a `config.json` file, which can be provided as a volume mount, downloaded from an HTTP URL, or set as a JSON environment variable.
It supports an SSE bridge (`/mcp-server/sse`) for external MCP clients. Authentication is enabled via API keys passed as a Bearer token in the `Authorization` header.
Streaming completions without MCP are not yet implemented. MCP resource support is planned but not currently available.
Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

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

Turn a plain-language guide into a narrated walkthrough video of your deployed web app. Your coding agent can write the guide from the source and bring back the MP4.
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci
Comments