# @sensigo/realm-cli

Source: https://glimind.com/server/npm%2F-sensigo%2Frealm-cli
Registry id: `npm/-sensigo/realm-cli`
Status: unknown

## Install

```json
{
  "mcpServers": {
    "sensigo-realm-cli": {
      "command": "npx",
      "args": [
        "-y",
        "@sensigo/realm-cli"
      ]
    }
  }
}
```

Claude Code:

```sh
claude mcp add sensigo-realm-cli -- npx -y @sensigo/realm-cli
```

## Tools (13)

- `abandon_run`
- `advance_run`: Run what a run owes the engine — an expired question's declared on_expiry, then its guards and automatic steps — in this server's environment. Call it when next
- `append_trace`
- `create_workflow`: Create a dynamic Realm workflow at runtime and immediately start a run. Use this when you have a multi-step task and want to track your own execution plan. Retu
- `execute_step`
- `fact`: fact
- `get_run_state`: Get the current state summary of a workflow run. Pass include_steps: true for each
- `get_workflow_protocol`: Get the full agent protocol briefing for a registered workflow.
- `list_workflows`: List all registered Realm workflows; names every registered copy that could not be read, and refuses when the registry directory itself cannot be read.
- `present_question`
- `start_run`: Create a new workflow run and run its first automatic steps.
- `start_run_batch`: Atomically enqueue multiple runs of the same workflow. No step runs; each started entry's next_actions names its first call. All items are validated before any 
- `submit_human_response`

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.
