Record an action the agent just took (e.g. edit "src/auth.ts").
AI agents use record_action to create or update resources in State Trace — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your State Trace environment.
This tool creates or modifies records in a memory/state system (a working memory graph) in a reversible manner. It does not delete data, execute external code, or cause financial transactions. The 'record' operation is a Write-category action—adding entries to a log or graph structure.
From the tool's definition Tool description states 'Record an action the agent just took', indicating it writes/appends a record to the state-trace working memory. The example 'edit "src/auth.ts"' shows it logs actions for memory tracking purposes.
Attacks that exploit this kind of access
Record an action the agent just took (e.g. edit "src/auth.ts"). It is categorised as a Write tool in the State Trace MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the State Trace MCP server in PolicyLayer and add a rule for record_action: 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.
record_action 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_action 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_action. 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_action 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 →