Rewrite the draft integrating evidence findings. Corrects contradicted claims, hedges mixed claims, and flags irreconcilable conflicts. IMPORTANT: If the draft was a refusal/non-answer (is_refusal from arsr_draft_response), pass original_query and is_refusal. The revision engine will then generat...
AI agents use arsr_revise_response to create or update resources in Mcp Arsr — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Arsr environment.
This tool creates or modifies text output (a response/answer) based on input evidence and uncertainty scores. It is reversible and has no side effects beyond generating new content. It does not execute code, retrieve new data, delete anything, or move money. The 'Write' category applies because the primary function is to generate or rewrite response text.
From the tool's definition Tool description states it 'Rewrite[s] the draft integrating evidence findings' and 'Corrects contradicted claims, hedges mixed claims, and flags irreconcilable conflicts.' The args include 'draft' (current text to revise) and evidence/scored arrays used to…
Attacks that exploit this kind of access
Rewrite the draft integrating evidence findings. Corrects contradicted claims, hedges mixed claims, and flags irreconcilable conflicts. IMPORTANT: If the draft was a refusal/non-answer (is_refusal from arsr_draft_response), pass original_query and is_refusal. The revision engine will then generate a COMPLETELY NEW answer from the evidence instead of trying to edit a non-answer. Args: - draft (string): The current draft to revise - evidence (array): Evidence from retrieve_evidence - scored (array): Scored claims from score_uncertainty - original_query (string, optional): The user. It is categorised as a Write tool in the Mcp Arsr MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Arsr MCP server in PolicyLayer and add a rule for arsr_revise_response: 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 Mcp Arsr. Nothing to install.
arsr_revise_response is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the arsr_revise_response 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 arsr_revise_response. 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.
arsr_revise_response is provided by the Mcp Arsr MCP server (jayarrowz/mcp-arsr). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →