Simple MCP Ollama Bridge

🚀 MCP LLM Bridge

A bridge connecting the Model Context Protocol (MCP) server with OpenAI-compatible Large Language Models (LLMs) such as Ollama.

This bridge serves as a crucial link between the MCP server and LLMs like Ollama. For more information about MCP developed by Anthropic, please refer to the following links:

• Resources
• Prompts
• Tools
• Sampling

🚀 Quick Start

# Installation
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 .

⚠️ Important Note

Reactivate the environment to use the keys in .env: source .venv/bin/activate

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

mcp_server_params=StdioServerParameters(
    command="uv",
    # Modify this line = must be an absolute path! Add the MCP fetch server in this directory (cloned from https://github.com/modelcontextprotocol/servers/)
    args=["--directory", "~/llms/mcp/mc-server-fetch/servers/src/fetch", "run", "mcp-server-fetch"],
    env=None
),
# llm_config=LLMConfig(
#     api_key=os.getenv("OPENAI_API_KEY"),
#     model=os.getenv("OPENAI_MODEL", "gpt-4o"),
#     base_url=None
# ),
llm_config=LLMConfig(
    api_key="ollama",  # Can be any string for local testing
    model="llama3.2",
    base_url="http://localhost:11434/v1"  # Point to the endpoint of your local model
)

💻 Usage Examples

Basic Usage

The above code shows the basic configuration of the bridge.

Advanced Usage - Additional Endpoint Support

This bridge is also compatible with any endpoint that implements the OpenAI API specification:

Ollama

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

📄 License

MIT

👥 Contribution

PRs are welcome.