# analyze

Analyze disagreements and find common ground. Actions: - run: Trigger analysis — extracts cruxes, clusters, consensus (deliberation_id; optional: model) - get_result: Get analysis result (deliberation_id; optional: round). While the analysis is running, returns {status:"pending", analysis_status: <stage>} with the current pipeline stage (taxonomy / extracting / crux_detection / clustering) so a single poll loop on this tool replaces calling deliberation action:get for progress. - cancel: Cancel in-progress analysis (deliberation_id) - propose_compromise: Generate a compromise statement (deliberation_id; optional: model) - reframe: Restate a position emphasizing common ground (deliberation_id, position_id; optional: model) - challenge: Challenge an analysis result (deliberation_id, agent_id, reason) - dispute_crux: Dispute a crux classification (deliberation_id, agent_id, crux_claim, correction) - expert_panel: Run an adversarial expert panel review (document; optional: topic, source_type, depth, experts, group_id, model). Creates a deliberation, submits expert critiques, triggers analysis. Returns deliberation_id immediately — poll with deliberation action:get for status, then analyze action:get_result. depth: "quick" (~2 min, 3 experts, tight taxonomy) or "thorough" (~7 min, 5 experts, full taxonomy). source_type selects specialized experts: "code_review", "architecture", "experiment", "proposal". - follow_up: Submit follow-up expert positions responding to round 1 cruxes, then trigger round 2 analysis (deliberation_id; optional: model). Experts review the cruxes and consensus, flag misclassifications, and identify missed issues. Requires round 1 to be complete.

Agent View of the PolicyLayer registry record for `analyze`. HTML page: https://policylayer.com/tools/dev-gemot-gemot/analyze

## Facts

- Tool: `analyze`
- Server: Gemot Deliberation Server (`https://gemot.dev/mcp`) — https://policylayer.com/tools/dev-gemot-gemot.md
- Homepage: https://github.com/justinstimatze/gemot
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- Server rate-limited: no
- Parameters: 12 (1 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `depth` | string | no |  |
| `model` | string | no |  |
| `round` | null | integer | no |  |
| `topic` | string | no |  |
| `action` | string | yes |  |
| `reason` | string | no |  |
| `experts` | string | no |  |
| `options` | null | array | no |  |
| `agent_id` | string | no |  |
| `document` | string | no |  |
| `group_id` | string | no |  |
| `correction` | string | no |  |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "analyze",
    "arguments": {
      "action": "<action>"
    }
  }
}
```

## Why analyze is rated High

The tool executes a multi-stage analysis pipeline (taxonomy, extracting, crux_detection, clustering) and triggers operations like compromise generation and cancellation. These are active executions of external processes rather than simple reads or writes, making Execute the most appropriate category. Severity is medium as misuse could disrupt deliberation processes but has limited broader blast radius.

From the tool's own definition: "'run: Trigger analysis — extracts cruxes, clusters, consensus', 'cancel: Cancel in-progress analysis', 'propose_compromise: Generate a compromise statement' — the tool triggers external pipeline operations and can cancel or generate outputs"

Risk signals: High parameter count (18 properties)

## Use case

AI agents invoke analyze to trigger actions in Gemot Deliberation Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Gemot Deliberation Server:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "analyze": {
      "limits": [
        {
          "counter": "analyze_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Gemot Deliberation Server (6)

- `deliberation` — Destructive — https://policylayer.com/tools/dev-gemot-gemot/deliberation.md
- `account` — Financial — https://policylayer.com/tools/dev-gemot-gemot/account.md
- `admin` — Read — https://policylayer.com/tools/dev-gemot-gemot/admin.md
- `decide` — Read — https://policylayer.com/tools/dev-gemot-gemot/decide.md
- `coordinate` — Write — https://policylayer.com/tools/dev-gemot-gemot/coordinate.md
- `participate` — Write — https://policylayer.com/tools/dev-gemot-gemot/participate.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=dev-gemot-gemot · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/dev-gemot-gemot