completeTodo · Remote MCP with Azure Container Apps MCP

WHAT IT DOES

What completeTodo does on Remote MCP with Azure Container Apps

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

WHY IT NEEDS A POLICY

Why completeTodo needs a policy

This tool modifies data reversibly by changing the completion status of a TODO item. It is not destructive because the original task data is preserved and can be unmarked if needed. It is not Execute because it does not run arbitrary code or scripts—it performs a bounded state transition on a specific resource.

From the tool's definition Tool description states 'Mark a TODO item as completed' and 'Returns a confirmation message or an error if the id does not exist', indicating it modifies the state of an existing task (marking it as completed/done).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

completeTodo Rate-limited

completeTodo 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": {
    "completeTodo": {
      "limits": [
        {
          "counter": "completetodo_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 Remote MCP with Azure Container Apps, so you can run agents against it safely.

FAQ

Questions about completeTodo

What does the completeTodo tool do? +

Mark a TODO item as completed. Provide the id of the task to mark as done. Returns a confirmation message or an error if the id does not exist. It is categorised as a Write tool in the Remote MCP with Azure Container Apps MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on completeTodo? +

Register the Remote MCP with Azure Container Apps MCP server in PolicyLayer and add a rule for completeTodo: 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 Remote MCP with Azure Container Apps. Nothing to install.

What risk level is completeTodo? +

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

Can I rate-limit completeTodo? +

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

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

completeTodo is provided by the Remote MCP with Azure Container Apps MCP server (powerstar13/copilot-mcp-poc). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.