mark_complete · Agent Communication MCP Server MCP

WHAT IT DOES

What mark_complete does on Agent Communication MCP Server

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

WHY IT NEEDS A POLICY

Why mark_complete needs a policy

This tool writes/modifies data (task completion status) reversibly. It does not delete data (not Destructive), execute external code (not Execute), or move money (not Financial). While it affects task tracking state, the operation is reversible through normal task management workflows.

From the tool's definition mark_complete modifies task state by changing completion status or error state, which are persistent state changes that are reversible (tasks can be reopened, reassigned, or reprocessed).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_complete Rate-limited

mark_complete 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": {
    "mark_complete": {
      "limits": [
        {
          "counter": "mark_complete_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 Communication MCP Server, so you can run agents against it safely.

FAQ

Questions about mark_complete

What does the mark_complete tool do? +

Mark task as complete or error with intelligent reconciliation for unchecked plan items. It is categorised as a Write tool in the Agent Communication MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on mark_complete? +

Register the Agent Communication MCP Server MCP server in PolicyLayer and add a rule for mark_complete: 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 Communication MCP Server. Nothing to install.

What risk level is mark_complete? +

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

Can I rate-limit mark_complete? +

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

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

mark_complete is provided by the Agent Communication MCP Server MCP server (jerfowler/agent-comm-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.