MCP Connect Hub

Configure, connect, and use Model Context Protocol tools with your favorite local LLM clients.

📖 How MCP Works

Model Context Protocol (MCP) standardizes how AI models interact with external tools, data, and APIs. You run an MCP Server locally or remotely, and your LLM client connects to it via stdio or HTTP/SSE.

⚙️ Client Setup Guides

  1. Open LM StudioSettings (⚙️) → Navigate to MCP Servers.
  2. Click Add Server and paste the JSON config generated below.
  3. Ensure Enable MCP is toggled on. Restart the app if prompted.
  4. Open a chat. Tools will appear automatically when the model requests them.

⚠️ LM Studio v0.3.5+ recommended. Paths/UI may shift slightly between releases.

  1. Locate your config: ~/.config/Claude/claude_desktop_config.json (Linux/Windows) or ~/Library/Application Support/Claude/claude_desktop_config.json (macOS).
  2. Create the file if it doesn't exist. Paste the generated JSON inside.
  3. Open Claude Desktop → Developer → Enable MCP (if not already on).
  4. Restart Claude. MCP tools will load automatically in new chats.

📁 Ensure the JSON is valid. Claude strictly validates on startup and will ignore malformed entries.

  1. Log into Open WebUI → Click your avatar → Admin Panel.
  2. Navigate to Settings → MCP tab.
  3. Click Add Server, paste the generated JSON, and save.
  4. If running via Docker, you can also mount a mcp_config.json via docker-compose.yml env vars.

💡 Open WebUI auto-reloads MCP configs. You may need to toggle "Use MCP Tools" in the chat settings.

  1. In your project root, create a .cursor folder (if it doesn't exist).
  2. Add mcp.json inside it and paste the generated JSON.
  3. Restart Cursor or run CMD/CTRL + SHIFT + PCursor: Reload Window.
  4. Open the AI Chat. MCP tools will be available in the agent/composer mode.

🔒 Workspace-scoped config means each project can have its own MCP tools. Great for repo-specific automation.

  1. Open VS Code / JetBrains → Click the Continue sidebar → ⚙️ Settings.
  2. Locate mcpServers in your config.json (usually ~/.continue/config.json).
  3. Paste the generated JSON into the mcpServers array/object.
  4. Save and reload the IDE. Continue will auto-detect and initialize the server.

🛠️ Continue supports both stdio and streamable-http. Use stdio for local Node/Python servers.

  1. Locate your client's MCP configuration file (usually mcp.json, config.json, or settings UI).
  2. Use the "mcpServers" key format shown in the generator below.
  3. Use stdio transport for local servers, sse or http for remote.
  4. Restart the client and verify tools load in the chat interface.

🛠️ MCP Config Generator

💡 One per line. Quotes around values are optional.

✅ Quick Validation Checklist

❤️ Enjoying MCP Connect Hub?

Replace placeholder links with your accounts • No tracking • 100% optional