AI agents use record_decision to create or update resources in Agent Bus — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Agent Bus environment.
The tool writes/stores a decision record with associated metadata (rationale, implemented flag) to a shared message bus or data store. This is a reversible write operation—it creates a new record but does not execute code, delete data, or involve financial transactions. Misuse could lead to incorrect decisions being recorded and acted upon by other agents, giving it medium severity.
From the tool's definition Persist a project decision with rationale and implemented flag
Attacks that exploit this kind of access
Persist a project decision with rationale and implemented flag. It is categorised as a Write tool in the Agent Bus MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Agent Bus MCP server in PolicyLayer and add a rule for 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 Agent Bus. Nothing to install.
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 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 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.
record_decision is provided by the Agent Bus MCP server (mustaphasteph/agent-bus). 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 →