Budgeted brief for small coding agents. Returns patch_file,
AI agents call retrieve_brief to retrieve information from State Trace without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves pre-computed memory state information for agents without side effects, mutations, or triggering external operations. It is a data query operation with no destructive, financial, or executable consequences. The bounded capacity and artifact-first design confirm it is a read-only retrieval mechanism.
From the tool's definition Tool name 'retrieve_brief' and description 'Budgeted brief for small coding agents. Returns patch_file' indicates data retrieval. The verb 'retrieve' and return of read-only content (a brief/patch file) without modification or execution.
Attacks that exploit this kind of access
Budgeted brief for small coding agents. Returns patch_file,. It is categorised as a Read tool in the State Trace MCP Server, which means it retrieves data without modifying state.
Register the State Trace MCP server in PolicyLayer and add a rule for retrieve_brief: 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 State Trace. Nothing to install.
retrieve_brief 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 retrieve_brief 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 retrieve_brief. 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.
retrieve_brief is provided by the State Trace MCP server (agent-pattern-labs/state-trace). 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 →