AI agents use arch_record_decision to create or update resources in Paparats — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Paparats environment.
The name 'arch_record_decision' implies creating or storing a record (an architectural decision), which maps to Write. Sibling tools like 'arch_record_component' and 'arch_record_lesson' follow the same pattern of recording/persisting data. No indication of deletion or execution. Confidence is lowered due to empty description.
From the tool's definition Tool name: arch_record_decision — empty description; name suggests recording/storing an architectural decision.
Attacks that exploit this kind of access
arch_record_decision. It is categorised as a Write tool in the Paparats MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Paparats MCP server in PolicyLayer and add a rule for arch_record_decision: 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 Paparats. Nothing to install.
arch_record_decision 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 arch_record_decision 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 arch_record_decision. 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.
arch_record_decision is provided by the Paparats MCP server (@paparats/cli). 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 →