Give Your Local AI Tool-Calling Superpowers with Open WebUI and MCP

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.

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. The 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. Create a docker-compose.yml : services: open-webui: image: ghcr.io/open-webui/open-webui:main environment: - OLLAMA BASE URL=http://ollama:11434 - MCP ENABLE=true - ENABLE TOOLS=true volumes: - open-webui:/app/backend/data ports: - "3000:8080" ollama: image: ollama/ollama:latest volumes: - ollama:/root/.ollama ports: - "11434:11434" deploy: resources: reservations: devices: - driver: nvidia count: all capabilities: gpu volumes: ollama: open-webui: docker compose up -d Pull a model with strong tool-calling: docker exec ollama ollama pull qwen3:14b:q8 0 Open http://localhost:3000 and create your admin account. Go to Admin Panel → Settings → External Tools in Open WebUI. npx -y @anthropic/mcp-server-brave-search npx -y @modelcontextprotocol/server-filesystem /allowed/path Configure each tool in the Open WebUI admin panel to give your AI real-world capabilities. Start a new chat and click the tools icon wrench next to the input box. Select which tools the AI can use, then ask: The AI decides when to call tools and incorporates results into its responses. With 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. Originally published on everylocalai.com