--- title: "Quickstart" description: "Start Mcpjungle gateway, register your first MCP server, and connect a client — all in under 5 minutes." --- This quickstart guide will show you how to: 1. Start the mcpjungle server locally using `docker compose` 2. Add the [context7](https://context7.com/) MCP server in mcpjungle 3. Connect your Claude Desktop to mcpjungle to access tools ## Start the server Fetch the `docker-compose.yaml` and start the mcpjungle server: ```bash curl -O https://raw.githubusercontent.com/mcpjungle/MCPJungle/refs/heads/main/docker-compose.yaml docker compose up -d ``` This exposes mcpjungle's streamable http mcp server at `http://localhost:8080/mcp` by default. ## Add an MCP server 1. Download the `mcpjungle` CLI on your local machine either using brew or directly from the [Releases Page](https://github.com/mcpjungle/MCPJungle/releases). ```bash brew install mcpjungle/mcpjungle/mcpjungle ``` 2. Add the context7 MCP server to mcpjungle using the CLI: ```bash mcpjungle register --name context7 --url https://mcp.context7.com/mcp ``` You should see output similar to this:

register context7 in mcpjungle

MCPJungle also includes a Dashboard UI at `http://localhost:8080/`. The dashboard is currently in Beta. ## Connect to mcpjungle In your Claude Desktop, add the configuration for mcpjungle MCP server: ```json { "mcpServers": { "mcpjungle": { "command": "npx", "args": [ "mcp-remote", "http://localhost:8080/mcp", "--allow-http" ] } } } ``` Once you have added the configuration, try asking Claude something simple: ```text Use context7 to get the documentation for `/lodash/lodash` ``` Claude will then attempt to call the `context7__get-library-docs` tool via Mcpjungle, which will return the documentation for the Lodash library.

claude calls context7 tool via mcpjungle

You now have a working MCP setup with a single unified endpoint. ## Next steps Add HTTP and STDIO-based MCP servers to your gateway. Configure Cursor, Copilot, or a custom agent to use Mcpjungle. Expose curated subsets of tools to specific agents or clients. Run Mcpjungle in enterprise mode with access control and observability.