{"type":"mcp_server","name":"ollama-mcp-bridge","description":"This repository provides a TypeScript bridge connecting local LLMs via Ollama to Model Context Protocol servers, enabling open-source models to utilize tools like filesystem operations, web search, and more.","category":"AI","language":"TypeScript","stars":976,"forks":52,"owner":"patruff","github_url":"https://github.com/patruff/ollama-mcp-bridge","homepage":null,"setup":"## Setup\n\n1. Install Ollama and required model:\n```bash\nollama pull qwen2.5-coder:7b-instruct\n```\n\n2. Install MCP servers:\n```bash\nnpm install -g @modelcontextprotocol/server-filesystem\nnpm install -g @modelcontextprotocol/server-brave-search\nnpm install -g @modelcontextprotocol/server-github\nnpm install -g @modelcontextprotocol/server-memory\nnpm install -g @patruff/server-flux\nnpm install -g @patruff/server-gmail-drive\n```\n\n3. Configure credentials:\n   - Set `BRAVE_API_KEY` for Brave Search\n   - Set `GITHUB_PERSONAL_ACCESS_TOKEN` for GitHub\n   - Set `REPLICATE_API_TOKEN` for Flux\n   - Run Gmail/Drive MCP auth: `node path/to/gmail-drive/index.js auth`\n   - For example node C:\\Users\\patru\\AppData\\Roaming\\npm\\node_modules\\@patruff\\server-gmail-drive\\dist\\index.js auth","tools":"## Available Tools\n\n1. Filesystem operations (Allows the LLM to interact with the local filesystem).\n2. Brave web search (Enables the LLM to perform web searches).\n3. GitHub interactions (Allows the LLM to interact with GitHub repositories).\n4. Google Drive & Gmail integration (Enables the LLM to access and manage emails and files on Google Drive).\n5. Memory/storage (Provides the LLM with persistent memory capabilities).\n6. Image generation with Flux (Allows the LLM to generate images).\n7. Multi-MCP support with dynamic tool routing (Enables the bridge to handle multiple MCP servers and route requests dynamically).\n8. Structured output validation for tool calls (Validates the structure of tool calls made by the LLM).\n9. Automatic tool detection from user prompts (Detects the appropriate tool to use based on user input).\n10. Robust process management for Ollama (Manages the Ollama process effectively).\n11. Detailed logging and error handling (Provides detailed logs and handles errors gracefully).","faq":null,"created_at":"2024-12-12T05:40:19+00:00","updated_at":"2025-03-28T23:54:59+00:00","source_url":"https://model-context-protocol.com/servers/ollama-mcp-bridge-local-llm-tools","related_articles":[]}