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:...
This record as markdown: /tools/dev-gemot-gemot/analyze.md
What analyze does on Gemot Deliberation Server
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.
| Parameter | Type | Required | Description |
|---|---|---|---|
depth | string | — | |
model | string | — | |
round | null | integer | — | |
topic | string | — | |
action | string | Yes | |
reason | string | — | |
experts | string | — | |
options | null | array | — | |
agent_id | string | — | |
document | string | — | |
group_id | string | — | |
correction | string | — |
Parameters from the server's own tool schema.
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 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 signalsHigh parameter count (18 properties)
Attacks that exploit this kind of access
The rule that runs analyze safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Gemot Deliberation Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For analyze, this is the rule to start with:
analyze stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Gemot Deliberation Server, apply this rule, and every analyze call is checked against it from then on.
Questions about 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. It is categorised as a Execute tool in the Gemot Deliberation Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
analyze accepts 12 parameters: depth, model, round, topic, action, reason, experts, options, agent_id, document, group_id, correction. Required: action. The full parameter table on this page comes from the server's own tool schema.
Register the Gemot Deliberation Server MCP server in PolicyLayer and add a rule for analyze: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Gemot Deliberation Server. Nothing to install.
analyze is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the analyze rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for analyze. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
analyze is provided by the Gemot Deliberation Server MCP server (https://gemot.dev/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Gemot Deliberation Server, and thousands of servers like it.
Across the catalogue