Harflow MCP Server

What the code does

We read the source, 1 h ago · rules 995398eba69f

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.

        subprocess.Popen([sys.executable, "-m", "harflow_mcp.workflows", "supervise", run_id, "--root", str(storage.root)], stdin=subprocess.DEVNULL, stdout=output, stderr=output, start_new_session=True, close_fds=True, env=child_environment(storage.state_layout))

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.

            version = subprocess.run([binary, "--version"], capture_output=True, text=True, timeout=5, check=False)

    environ = dict(os.environ)

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 harflow-mcp -- uvx harflow-mcp

{
  "mcpServers": {
    "harflow-mcp": {
      "command": "uvx",
      "args": [
        "harflow-mcp"
      ]
    }
  }
}

[mcp_servers.harflow-mcp]
command = "uvx"
args = ["harflow-mcp"]

{
  "mcpServers": {
    "harflow-mcp": {
      "command": "uvx",
      "args": [
        "harflow-mcp"
      ]
    }
  }
}

{
  "servers": {
    "harflow-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "harflow-mcp"
      ]
    }
  }
}