AI agents call arsr_draft_response to retrieve information from Mcp Arsr without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or synthesizes information to answer a query within a closed-loop refinement system. It generates text output but does not create persistent data, modify systems, execute external commands, delete information, or handle financial transactions.
From the tool's definition Tool description states it 'Generate[s] an initial candidate response to a user query' and acknowledges 'The draft is generated by an inner LLM and may contain inaccuracies', indicating retrieval and synthesis of information without modifying external data or…
Attacks that exploit this kind of access
Generate an initial candidate response to a user query. This is the first step in the ARSR refinement loop. The draft is generated by an inner LLM and may contain inaccuracies — that. It is categorised as a Read tool in the Mcp Arsr MCP Server, which means it retrieves data without modifying state.
Register the Mcp Arsr MCP server in PolicyLayer and add a rule for arsr_draft_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_draft_response 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 arsr_draft_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_draft_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_draft_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 →