trace_save · Agent Safety MCP: Risk & Policy

WHAT IT DOES

What trace_save does on Agent Safety

AI agents use trace_save to create or update resources in Agent Safety — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Agent Safety environment.

WHY IT NEEDS A POLICY

Why trace_save needs a policy

This tool creates/writes files to disk (JSON and Markdown outputs of audit trace data). While not destructive (files can be deleted or overwritten), and not reading/querying existing data, it irreversibly commits trace information to storage.

From the tool's definition Tool performs 'Save the current trace to disk as JSON and Markdown files' — a write operation that creates new files with trace data on persistent storage.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

trace_save Rate-limited

trace_save stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "trace_save": {
      "limits": [
        {
          "counter": "trace_save_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Agent Safety, so you can run agents against it safely.

FAQ

Questions about trace_save

What does the trace_save tool do? +

Save the current trace to disk as JSON and Markdown files. It is categorised as a Write tool in the Agent Safety MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on trace_save? +

Register the Agent Safety MCP server in PolicyLayer and add a rule for trace_save: 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 Safety. Nothing to install.

What risk level is trace_save? +

trace_save is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit trace_save? +

Yes. Add a rate_limit block to the trace_save 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.

How do I block trace_save completely? +

Set action: deny in the PolicyLayer policy for trace_save. 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.

What MCP server provides trace_save? +

trace_save is provided by the Agent Safety MCP server (luciferforge/agent-safety-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.