TAR Engine MCP Server

What the code does

We read the source, 15 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.

            r = subprocess.run(

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.

        out = subprocess.check_output(

API_BASE = "https://api.telegram.org/bot{token}"

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 tar-engine -- uvx tar-engine

{
  "mcpServers": {
    "tar-engine": {
      "command": "uvx",
      "args": [
        "tar-engine"
      ]
    }
  }
}

[mcp_servers.tar-engine]
command = "uvx"
args = ["tar-engine"]

{
  "mcpServers": {
    "tar-engine": {
      "command": "uvx",
      "args": [
        "tar-engine"
      ]
    }
  }
}

{
  "servers": {
    "tar-engine": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "tar-engine"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: TAR_ENGINE_URL (Override the audit backend. Default is the hosted playground at https://tarai.dev. Set to http://localhost:8765 (or your own tar-engine deployment) to self-host and keep SKILL.md content on your machine), TAR_ENGINE_BYOK_OPENAI_KEY (OpenAI API key that unlocks the semantic LLM and adversarial prompt-fuzz layers. Static and supply-chain layers run without it), TAR_ENGINE_BYOK_ANTHROPIC_KEY (Anthropic API key alternative to the OpenAI key for the semantic and adversarial layers).