Umbra open SAR archive MCP Server

What the code does

We read the source, 23 h ago · rules 3dff92dd89df

Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.

файл ставится пользователю, в репозитории его нет, и в нём есть опасный вызов

os.setuid(u.pw_uid)

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.

        return __import__(module)

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 umbra-mcp -- uvx umbra-py

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

[mcp_servers.umbra-mcp]
command = "uvx"
args = ["umbra-py"]

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

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

This one needs environment variables set before it will start: UMBRA_CANOPY_TOKEN (Canopy API token. Set it and the same search tools query Umbra's authenticated commercial archive instead of the open bucket; leave it unset for the open data, which needs no credentials.), UMBRA_INDEX_DB (Path to a local catalog index (built with 'umbra index build' or fetched with 'umbra index fetch'). Without one the server walks the public bucket per search, which is correct but slow.), ANTHROPIC_API_KEY (Enables the two opt-in model tools, describe_scene and narrate_change. Every other tool is deterministic and calls no model.), OPENAI_API_KEY (Alternative provider for the same two model tools, and the encoder behind find_similar_text.). The author declared them in the registry entry; get the values from the project itself.