📌Overview

Purpose: To provide a seamless connection between Model Context Protocol (MCP) servers and OpenAI-compatible language models (LLMs) through an efficient protocol translation layer.

Overview: The MCP LLM Bridge acts as a bidirectional interface that translates MCP tool specifications to OpenAI function schemas. This allows any OpenAI-compatible model, including both cloud-based solutions and local implementations, to utilize MCP-compliant tools via a standardized method.

Key Features:

• Bidirectional Protocol Translation: Facilitates real-time communication between MCP servers and OpenAI's function-calling interface, enabling smooth tool execution and function invocation.

• Compatibility with Various Endpoints: Supports not only the primary OpenAI API but also local endpoints adhering to the OpenAI API specification, such as Ollama and LM Studio, enhancing flexibility and usability.

---

MCP LLM Bridge

A bridge connecting Model Context Protocol (MCP) servers to OpenAI-compatible LLMs. It offers primary support for the OpenAI API and compatibility with local endpoints implementing the OpenAI API specification.

The implementation provides a bidirectional protocol translation layer between MCP and OpenAI's function-calling interface. It converts MCP tool specifications into OpenAI function schemas and handles the mapping of function invocations back to MCP tool executions, allowing any OpenAI-compatible language model to utilize MCP-compliant tools.

Quick Start

# Install
curl -LsSf https://astral.sh/uv/install.sh | sh
git clone https://github.com/bartolli/mcp-llm-bridge.git
cd mcp-llm-bridge
uv venv
source .venv/bin/activate
uv pip install -e .

# Create test database
python -m mcp_llm_bridge.create_test_db

Configuration

OpenAI (Primary)

Create .env:

OPENAI_API_KEY=your_key
OPENAI_MODEL=gpt-4o # or any other OpenAI model that supports tools

Reactivate the environment if needed: source .venv/bin/activate

Then configure the bridge in src/mcp_llm_bridge/main.py:

config = BridgeConfig(
    mcp_server_params=StdioServerParameters(
        command="uvx",
        args=["mcp-server-sqlite", "--db-path", "test.db"],
        env=None
    ),
    llm_config=LLMConfig(
        api_key=os.getenv("OPENAI_API_KEY"),
        model=os.getenv("OPENAI_MODEL", "gpt-4o"),
        base_url=None
    )
)

Additional Endpoint Support

The bridge also works with any endpoint implementing the OpenAI API specification.

Ollama

llm_config=LLMConfig(
    api_key="not-needed",
    model="mistral-nemo:12b-instruct-2407-q8_0",
    base_url="http://localhost:11434/v1"
)

LM Studio

llm_config=LLMConfig(
    api_key="not-needed",
    model="local-model",
    base_url="http://localhost:1234/v1"
)

Usage

python -m mcp_llm_bridge.main

# Try: "What are the most expensive products in the database?"
# Exit with 'quit' or Ctrl+C

Running Tests

Install the package with test dependencies:

uv pip install -e ".[test]"

Then run the tests:

python -m pytest -v tests/

License

MIT

Contributing

PRs welcome.