ollama-mcp-bridge
Extend the Ollama API with dynamic AI tool integration from multiple MCP (Model Context Protocol) servers. Fully compatible, transparent, and developer-friendly, ideal for building powerful local LLM applications, AI agents, and custom chatbots
Ollama MCP Bridge is a proxy layer that sits in front of the Ollama API, seamlessly adding tools from multiple MCP servers so that every Ollama request can access all connected tools transparently. It supports streaming, thinking mode, tool filtering, and multiple transport types. The bridge is configurable via JSON, runs as a FastAPI server, and can be installed via pip, uvx, Docker, or from source.
Features
Compatibility
Quick start
Use cases
Alternatives
Related searches
Comments
- BBlake NguyenApr 15, 2026
Dynamic MCP tool integration into Ollama extends local models far beyond their defaults
- OOakley JacksonMar 25, 2026
Works fine on Mac with Ollama running locally, minimal latency overhead
- PPeyton LewisMar 19, 2026
The bridge pattern means local models can access the same tools as Claude
- RRiver AndersonMar 11, 2026
Good for privacy-sensitive workflows where you want local inference with external tool access