log_search_feedback · Chronos MCP: Risk & Policy

WHAT IT DOES

What log_search_feedback does on Chronos MCP

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

WHY IT NEEDS A POLICY

Why log_search_feedback needs a policy

The name implies logging (writing) search feedback to the persistent memory/knowledge graph system. Without a description, confidence is low. Logging is typically a Write operation, but the exact behavior is unknown. Given sibling tools involve memory management, this likely records feedback about search queries to improve relevance — a reversible write operation.

From the tool's definition Tool name 'log_search_feedback' suggests writing/recording feedback data; description is empty and uninformative.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

log_search_feedback Rate-limited

log_search_feedback 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": {
    "log_search_feedback": {
      "limits": [
        {
          "counter": "log_search_feedback_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 Chronos MCP, so you can run agents against it safely.

FAQ

Questions about log_search_feedback

What does the log_search_feedback tool do? +

log_search_feedback. It is categorised as a Write tool in the Chronos MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on log_search_feedback? +

Register the Chronos MCP server in PolicyLayer and add a rule for log_search_feedback: 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 Chronos MCP. Nothing to install.

What risk level is log_search_feedback? +

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

Can I rate-limit log_search_feedback? +

Yes. Add a rate_limit block to the log_search_feedback 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 log_search_feedback completely? +

Set action: deny in the PolicyLayer policy for log_search_feedback. 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 log_search_feedback? +

log_search_feedback is provided by the Chronos MCP server (kodaxadev/chronosmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.