analyze
Analyze recent runs from the opt-in debug log (latency/tokens/reasoning-effort per model) plus the session store (verdict agreement rate), and return advisory tuning suggestions (disable a slow/redundant model in ask-all, lower an OpenRouter model
This record as markdown: /tools/deliberation/analyze.md
What analyze does on Deliberation
AI agents call analyze to retrieve information from Deliberation without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why analyze is rated Low
The tool performs read-only analysis of logs and session data to generate advisory suggestions. It does not create, modify, delete, or execute any operations. There is no side effect beyond returning informational output. The low severity reflects minimal blast radius—misuse would only produce incorrect tuning advice, not harm external systems or data integrity.
From the tool's definition Tool description indicates it "Analyze[s] recent runs from the opt-in debug log" and queries "the session store" to "return advisory tuning suggestions." The verb "analyze" combined with "return" describes retrieval and analysis of existing telemetry data…
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 Deliberation, 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 is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Deliberation, apply this rule, and every analyze call is checked against it from then on.
Questions about analyze
Analyze recent runs from the opt-in debug log (latency/tokens/reasoning-effort per model) plus the session store (verdict agreement rate), and return advisory tuning suggestions (disable a slow/redundant model in ask-all, lower an OpenRouter model. It is categorised as a Read tool in the Deliberation MCP Server, which means it retrieves data without modifying state.
Register the Deliberation 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 Deliberation. Nothing to install.
analyze is a Read tool with low risk. Read-only tools are generally safe to allow by default.
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 Deliberation MCP server (antonbabenko/deliberation). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Deliberation, and thousands of servers like it.
This server
Across the catalogue