complete_task · Claude Session Continuity MCP: Risk & Policy

WHAT IT DOES

What complete_task does on Claude Session Continuity

AI agents use complete_task 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 complete_task needs a policy

This tool modifies task records by changing their completion status, making it a Write operation. It is reversible (tasks can typically be marked incomplete again) and has medium severity because misuse could alter project tracking state and mislead about work progress, but does not delete data or execute arbitrary code.

From the tool's definition Tool name 'complete_task' and description '태스크를 완료 처리합니다' (marks a task as complete/finished) indicates modification of task state. The Korean description translates to 'Completes/finishes a task', showing state change without deletion.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

complete_task Rate-limited

complete_task 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": {
    "complete_task": {
      "limits": [
        {
          "counter": "complete_task_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 complete_task

What does the complete_task tool do? +

태스크를 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 complete_task? +

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

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

Can I rate-limit complete_task? +

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

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

complete_task 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.