Orca MCP Server

What the code does

We read the source, 4 d ago · rules 995398eba69f

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.

            meta = pickle.load(f)

    const stdout = execSync(cmd, { cwd, encoding: 'utf-8', timeout, maxBuffer: 10 * 1024 * 1024 });

        proc = subprocess.run(

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 orca-mcp-server -- npx -y @orcalang/orca-mcp-server

{
  "mcpServers": {
    "orca-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@orcalang/orca-mcp-server"
      ]
    }
  }
}

[mcp_servers.orca-mcp-server]
command = "npx"
args = ["-y", "@orcalang/orca-mcp-server"]

{
  "mcpServers": {
    "orca-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@orcalang/orca-mcp-server"
      ]
    }
  }
}

{
  "servers": {
    "orca-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@orcalang/orca-mcp-server"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: ANTHROPIC_API_KEY (Anthropic API key for LLM-powered tools (generate_machine, generate_multi_machine, refine_machine, generate_actions with use_llm). Not required for parse_machine, verify_machine, compile_machine, or server_status), ORCA_PROVIDER (LLM provider to use: anthropic (default), openai, grok, or ollama), ORCA_MODEL (Model name to use for LLM tools. Defaults to claude-sonnet-4-6 for Anthropic).