Skip to content
ToolMesh

Getting Started

ToolMesh runs as a single Go binary or Docker container. It exposes an MCP server that AI agents connect to.

Prerequisites

Section titled “Prerequisites”
  • Docker (recommended) or Go 1.25+
  • An AI agent that speaks MCP (Claude Desktop, Claude Code, or any MCP client)

Quick Start with Docker

Section titled “Quick Start with Docker”
Terminal window
docker run -d \
  --name toolmesh \
  -p 8123:8080 \
  -e TOOLMESH_AUTH_PASSWORD=changeme \
  -e CREDENTIAL_GITHUB_TOKEN=ghp_xxxxx \
  -v ./config:/app/config \
  -v ./dadl:/app/dadl \
  dunkelcloud/toolmesh:latest

ToolMesh is now running on http://localhost:8123.

Quick Start with Go

Section titled “Quick Start with Go”
Terminal window
git clone https://github.com/DunkelCloud/ToolMesh.git
cd ToolMesh
make build
./toolmesh

Connect an AI Agent

Section titled “Connect an AI Agent”

Claude Desktop

Section titled “Claude Desktop”

Add to your Claude Desktop MCP config (claude_desktop_config.json):

{
  "mcpServers": {
    "toolmesh": {
      "url": "http://localhost:8123/mcp"
    }
  }
}

Claude Code

Section titled “Claude Code”
Terminal window
claude mcp add toolmesh http://localhost:8123/mcp

Add a Backend

Section titled “Add a Backend”

Backends are configured in config/backends.yaml.

MCP Backend (proxy an existing MCP server)

Section titled “MCP Backend (proxy an existing MCP server)”
backends:
  - name: memorizer
    transport: http
    url: "https://memorizer.example.com/mcp"
    api_key_env: "MEMORIZER_API_KEY"

REST Backend (via DADL)

Section titled “REST Backend (via DADL)”
backends:
  - name: github
    transport: rest
    dadl: /app/dadl/github.dadl
    url: "https://api.github.com"

Download DADL files from the DADL Registry or generate one with your LLM.

What’s Next

Section titled “What’s Next”