Claude Flow MCP Server

What the code does

We read the source, 7 d ago · rules 3dff92dd89df

A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.

        existsSync(registryPath) ? JSON.parse(readFileSync(registryPath, 'utf-8')) : {};

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

  const child = spawn(process.execPath, [cliBin, 'daemon', 'start', '--quiet'], {

      const cfg = JSON.parse(fs.readFileSync(path.join(projectRoot, file), 'utf-8'));

# Switch to root for patching and file operations
USER root

# Bake .env.local with MODELS config (too large for Cloud Run env vars)

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

claude mcp add claude-flow -- npx -y claude-flow

{
  "mcpServers": {
    "claude-flow": {
      "args": [
        "-y",
        "claude-flow"
      ],
      "command": "npx"
    }
  }
}

[mcp_servers.claude-flow]
command = "npx"
args = ["-y", "claude-flow"]

{
  "mcpServers": {
    "claude-flow": {
      "args": [
        "-y",
        "claude-flow"
      ],
      "command": "npx"
    }
  }
}

{
  "mcpServers": {
    "claude-flow": {
      "args": [
        "-y",
        "claude-flow"
      ],
      "command": "npx"
    }
  }
}

This one needs environment variables set before it will start: ANTHROPIC_API_KEY (Anthropic API key for Claude AI models), CLAUDE_FLOW_MODE (Operation mode: development, production, or test), CLAUDE_FLOW_MEMORY_PATH (Path for persistent memory storage), CLAUDE_FLOW_MAX_AGENTS (Maximum number of concurrent agents), CLAUDE_FLOW_PORT (MCP server port), GITHUB_TOKEN (GitHub personal access token for repository operations), FLOW_NEXUS_API_KEY (Flow Nexus cloud platform API key). The author declared them in the registry entry; get the values from the project itself.