Back to MCP Servers
🔌

freema/openclaw-mcp

MITAPI key required

](https://glama.ai/mcp/servers/@freema/openclaw-mcp) 📇 ☁️ 🏠 - MCP server for AI assistant integration. Enables Claude to delegate tasks to OpenClaw agents with sync/async tools, OAuth 2.1 auth, and

TypeScriptAI & LLMs

Install

npx -y openclaw-mcp

Required environment variables

OPENCLAW_GATEWAY_TOKENSet in your MCP config
MCP_CLIENT_SECRETSet in your MCP config

claude_desktop_config.json

claude_desktop_config.json
{
  "mcpServers": {
    "freema-openclaw-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "openclaw-mcp"
      ],
      "env": {
        "OPENCLAW_GATEWAY_TOKEN": "<YOUR_OPENCLAW_GATEWAY_TOKEN>",
        "MCP_CLIENT_SECRET": "<YOUR_MCP_CLIENT_SECRET>"
      }
    }
  }
}

Add this to your Claude Desktop config file. Find it at ~/Library/Application Support/Claude/claude_desktop_config.json on macOS.

What this does

freema/openclaw-mcp exposes a set of tools to Claude over the Model Context Protocol. After you add it to claude_desktop_config.json (snippet above) and restart Claude Desktop, those tools become callable inside any conversation. That makes it useful when you want Claude to reach into other AI providers and LLM tooling without copy-pasting context every turn.

Requirements

This server needs the following environment variables to be set before it can run:

OPENCLAW_GATEWAY_TOKEN
MCP_CLIENT_SECRET

Set these via the env object in your MCP config (see claude_desktop_config.json snippet above).

Common use cases

  • Delegate reasoning to a different model or LLM provider from a Claude session
  • Pull live model documentation, rate limits, or usage data into context
  • Chain Claude with another agent or evaluation pipeline