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
What is Ollama MCP Bridge?
Ollama MCP Bridge is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 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 ...
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
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Extend the Ollama API with dynamic AI tool integration from
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx ollama-mcp-bridgeConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Ollama MCP Bridge
Ollama MCP Bridge extends the Ollama API with dynamic AI tool integration by acting as a transparent proxy between Ollama-powered local LLMs and any number of MCP servers. Instead of Ollama models only having access to their built-in capabilities, the bridge fetches available tools from configured MCP servers at runtime and injects them into the Ollama chat API, enabling fully local LLM applications to use file system access, web search, GitHub integration, email, and image generation as first-class tools. Developers building local AI agents or custom chatbots with Ollama gain MCP compatibility without requiring a cloud-based LLM or modifying Ollama itself.
Prerequisites
- Ollama installed and running locally with at least one model pulled (e.g. llama3)
- Node.js 18+ for running the bridge
- One or more MCP servers to connect (e.g. filesystem, brave-search, github)
- API keys for any external MCP servers you want to use (e.g. BRAVE_API_KEY, GITHUB_PERSONAL_ACCESS_TOKEN)
- Optional: REPLICATE_API_TOKEN for image generation via Flux
Clone the Ollama MCP Bridge repository
Clone the bridge repository from GitHub to get the source code and default configuration.
git clone https://github.com/patruff/ollama-mcp-bridge.git
cd ollama-mcp-bridgeInstall dependencies
Install the required MCP server packages and bridge dependencies.
npm install -g @modelcontextprotocol/server-filesystem
npm install -g @modelcontextprotocol/server-brave-search
npm install -g @modelcontextprotocol/server-github
npm install -g @modelcontextprotocol/server-memory
npm installConfigure environment variables
Set the API keys required by the MCP servers you plan to use. The bridge reads these from the environment and passes them to the individual MCP server processes.
export BRAVE_API_KEY=your_brave_api_key
export GITHUB_PERSONAL_ACCESS_TOKEN=your_github_token
export REPLICATE_API_TOKEN=your_replicate_tokenStart the bridge
Launch the Ollama MCP Bridge. It starts a local server that proxies the Ollama API while dynamically loading tools from all configured MCP servers.
npm run startConnect via the extended Ollama API
Use the bridge's API endpoint in place of the standard Ollama endpoint. Your local LLM can now call MCP tools transparently. Use 'list-tools' to see available tools.
# List available tools
curl http://localhost:3000/list-tools
# Chat with tool access
curl http://localhost:3000/api/chat -d '{"model":"llama3","messages":[{"role":"user","content":"Search the web for latest Node.js features"}]}' Ollama MCP Bridge Examples
Client configuration
MCP configuration for using the Ollama MCP Bridge as an MCP server within Claude Desktop.
{
"mcpServers": {
"ollama-mcp-bridge": {
"command": "npx",
"args": ["ollama-mcp-bridge"],
"env": {
"BRAVE_API_KEY": "your_brave_key",
"GITHUB_PERSONAL_ACCESS_TOKEN": "your_github_token"
}
}
}
}Prompts to try
Example prompts and commands demonstrating what the Ollama MCP Bridge enables local LLMs to do through tool integration.
- "Search the web for the latest TypeScript 5.0 features"
- "Create a new folder called project-docs in my home directory"
- "Look up the open issues in the patruff/ollama-mcp-bridge GitHub repo"
- "Remember that my project deadline is June 30th"
- "Generate an image of a futuristic robot assistant"Troubleshooting Ollama MCP Bridge
Bridge starts but tools are not available in LLM responses
Run 'curl http://localhost:3000/list-tools' to verify MCP servers are loaded. Ensure each MCP server package is globally installed and accessible on your PATH.
Ollama model not found or connection refused
Verify Ollama is running with 'ollama serve' and that you have pulled the model you are using with 'ollama pull llama3'. The bridge defaults to connecting to Ollama at http://localhost:11434.
Web search MCP tool fails with authentication error
Ensure BRAVE_API_KEY is exported in the same shell session where the bridge runs. Get a free Brave Search API key at https://brave.com/search/api/.
Frequently Asked Questions about Ollama MCP Bridge
What is Ollama MCP Bridge?
Ollama MCP Bridge is a Model Context Protocol (MCP) server that 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 It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Ollama MCP Bridge?
Follow the installation instructions on the Ollama MCP Bridge GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Ollama MCP Bridge?
Ollama MCP Bridge works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Ollama MCP Bridge free to use?
Yes, Ollama MCP Bridge is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Ollama MCP Bridge Alternatives — Similar Data Science & ML Servers
Looking for alternatives to Ollama MCP Bridge? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Ollama MCP Bridge in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Ollama MCP Bridge?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.