{"slug": "give-your-local-ai-tool-calling-superpowers-with-open-webui-and-mcp", "title": "Give Your Local AI Tool-Calling Superpowers with Open WebUI and MCP", "summary": "Open WebUI now supports the Model Context Protocol (MCP), enabling local AI assistants to use external tools like web search, file access, and code execution. Developers can set up a Docker-based environment with Ollama and Open WebUI, configure MCP servers, and achieve tool-calling performance of 3-5 seconds on an RTX 4070 Super. All data remains on the user's machine.", "body_md": "Want a ChatGPT-like experience where your AI can search the web, read your files, query databases, and run code? Open WebUI + MCP makes it possible - all running locally on your hardware.\n\nThe Model Context Protocol (MCP) is an open standard that lets AI connect to external tools. Open WebUI supports MCP natively, turning your local Ollama setup into a tool-equipped AI assistant.\n\nCreate a `docker-compose.yml`\n\n:\n\n```\nservices:\n  open-webui:\n    image: ghcr.io/open-webui/open-webui:main\n    environment:\n      - OLLAMA_BASE_URL=http://ollama:11434\n      - MCP_ENABLE=true\n      - ENABLE_TOOLS=true\n    volumes:\n      - open-webui:/app/backend/data\n    ports:\n      - \"3000:8080\"\n\n  ollama:\n    image: ollama/ollama:latest\n    volumes:\n      - ollama:/root/.ollama\n    ports:\n      - \"11434:11434\"\n    deploy:\n      resources:\n        reservations:\n          devices:\n            - driver: nvidia\n              count: all\n              capabilities: [gpu]\n\nvolumes:\n  ollama:\n  open-webui:\ndocker compose up -d\n```\n\nPull a model with strong tool-calling:\n\n```\ndocker exec ollama ollama pull qwen3:14b:q8_0\n```\n\nOpen ** http://localhost:3000** and create your admin account.\n\nGo to **Admin Panel → Settings → External Tools** in Open WebUI.\n\n```\nnpx -y @anthropic/mcp-server-brave-search\nnpx -y @modelcontextprotocol/server-filesystem /allowed/path\n```\n\nConfigure each tool in the Open WebUI admin panel to give your AI real-world capabilities.\n\nStart a new chat and click the tools icon (wrench) next to the input box. Select which tools the AI can use, then ask:\n\nThe AI decides when to call tools and incorporates results into its responses.\n\nWith Qwen3 14B Q8 on an RTX 4070 Super: tool calls complete in 3-5 seconds. Web search results are returned in 2-3 seconds. All data stays on your machine.\n\n*Originally published on everylocalai.com*", "url": "https://wpnews.pro/news/give-your-local-ai-tool-calling-superpowers-with-open-webui-and-mcp", "canonical_source": "https://dev.to/everylocalai/give-your-local-ai-tool-calling-superpowers-with-open-webui-and-mcp-3jdi", "published_at": "2026-06-14 22:07:37+00:00", "updated_at": "2026-06-14 22:40:40.897167+00:00", "lang": "en", "topics": ["ai-tools", "developer-tools", "large-language-models", "ai-infrastructure"], "entities": ["Open WebUI", "Model Context Protocol", "Ollama", "Qwen3", "RTX 4070 Super", "Docker", "NVIDIA"], "alternates": {"html": "https://wpnews.pro/news/give-your-local-ai-tool-calling-superpowers-with-open-webui-and-mcp", "markdown": "https://wpnews.pro/news/give-your-local-ai-tool-calling-superpowers-with-open-webui-and-mcp.md", "text": "https://wpnews.pro/news/give-your-local-ai-tool-calling-superpowers-with-open-webui-and-mcp.txt", "jsonld": "https://wpnews.pro/news/give-your-local-ai-tool-calling-superpowers-with-open-webui-and-mcp.jsonld"}}