resolve_feedback · Claude Session Continuity MCP

WHAT IT DOES

What resolve_feedback does on Claude Session Continuity

AI agents use resolve_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 resolve_feedback needs a policy

The tool creates or modifies feedback state within the session context system, making it a Write operation. It's not Read (retrieves data), Execute (runs arbitrary commands), Destructive (irreversible deletion), or Financial. Severity is medium because misuse could alter project feedback records, but the scope is limited to session-local context data rather than permanent external systems.

From the tool's definition Tool name 'resolve_feedback' and description 'resolves/completes feedback' (Korean: 피드백을 해결 완료 처리합니다 = 'marks feedback as resolved/completed'). This modifies feedback state in the session continuity system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

resolve_feedback Rate-limited

resolve_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": {
    "resolve_feedback": {
      "limits": [
        {
          "counter": "resolve_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 resolve_feedback

What does the resolve_feedback tool do? +

피드백을 해결 완료 처리합니다. 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 resolve_feedback? +

Register the Claude Session Continuity MCP server in PolicyLayer and add a rule for resolve_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 resolve_feedback? +

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

Can I rate-limit resolve_feedback? +

Yes. Add a rate_limit block to the resolve_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 resolve_feedback completely? +

Set action: deny in the PolicyLayer policy for resolve_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 resolve_feedback? +

resolve_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.