consensus
Run the FULL multi-round consensus convergence loop server-side with a provider arbiter (blind pass + peer fan-out -> adjudicate -> revise) and return the converged verdict. Default depth is
This record as markdown: /tools/deliberation/consensus.md
What consensus does on Deliberation
AI agents invoke consensus to trigger actions in Deliberation. 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.
Why consensus is rated High
The tool triggers a complex multi-step workflow that executes external operations (querying 400+ models) with side effects dependent on argument configuration (providers, depth, adjudication logic). While it does not delete or modify persistent data (hence not Destructive), it performs server-side computation and external API orchestration that generates new outputs and state changes across multiple rounds.
From the tool's definition Tool runs a 'FULL multi-round consensus convergence loop server-side' with 'blind pass + peer fan-out -> adjudicate -> revise' operations.
Attacks that exploit this kind of access
The rule that runs consensus 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 consensus, this is the rule to start with:
consensus 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 Deliberation, apply this rule, and every consensus call is checked against it from then on.
Questions about consensus
Run the FULL multi-round consensus convergence loop server-side with a provider arbiter (blind pass + peer fan-out -> adjudicate -> revise) and return the converged verdict. Default depth is. It is categorised as a Execute tool in the Deliberation MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Deliberation MCP server in PolicyLayer and add a rule for consensus: 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.
consensus 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 consensus 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 consensus. 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.
consensus 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.
Across the catalogue