collect_work_feedback · Claude Session Continuity MCP

WHAT IT DOES

What collect_work_feedback does on Claude Session Continuity

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

WHY IT NEEDS A POLICY

Why collect_work_feedback needs a policy

The tool collects and records feedback data upon work completion. This is a Write operation as it stores/logs feedback entries. It does not delete data, execute code, or involve financial transactions. The description is in Korean and somewhat limited in detail, which slightly reduces confidence, but 'records' (기록합니다) clearly implies writing data. Severity is low as it only captures feedback metadata.

From the tool's definition '피드백을 수집합니다. 에러, 타임아웃, 불편사항 등을 기록합니다' — collects and records feedback (errors, timeouts, inconveniences) upon task completion

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

collect_work_feedback Rate-limited

collect_work_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": {
    "collect_work_feedback": {
      "limits": [
        {
          "counter": "collect_work_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 Claude Session Continuity, so you can run agents against it safely.

FAQ

Questions about collect_work_feedback

What does the collect_work_feedback tool do? +

/work 작업 완료 시 자동으로 피드백을 수집합니다. 에러, 타임아웃, 불편사항 등을 기록합니다. It is categorised as a Write tool in the Claude Session Continuity MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on collect_work_feedback? +

Register the Claude Session Continuity MCP server in PolicyLayer and add a rule for collect_work_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 Claude Session Continuity. Nothing to install.

What risk level is collect_work_feedback? +

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

Can I rate-limit collect_work_feedback? +

Yes. Add a rate_limit block to the collect_work_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 collect_work_feedback completely? +

Set action: deny in the PolicyLayer policy for collect_work_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 collect_work_feedback? +

collect_work_feedback is provided by the Claude Session Continuity MCP server (leesgit/claude-session-continuity-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.