resolve-todo · Mmc MCP: Risk & Policy

WHAT IT DOES

What resolve-todo does on Mmc

AI agents use resolve-todo to create or update resources in Mmc — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mmc environment.

WHY IT NEEDS A POLICY

Why resolve-todo needs a policy

The tool modifies the state of a todo item by marking it resolved and removing it from the active list. This is a state mutation but appears reversible (unlike deletion). It does not execute arbitrary code, move money, or permanently destroy data. The business process context suggests this is part of normal workflow progression.

From the tool's definition Tool description states 'Mark a claimed todo as completed/resolved. The todo is removed from the active task list.' – this modifies state by removing items from an active task list, which is a reversible write operation (todos can typically be re-added or…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

resolve-todo Rate-limited

resolve-todo 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-todo": {
      "limits": [
        {
          "counter": "resolve-todo_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 Mmc, so you can run agents against it safely.

FAQ

Questions about resolve-todo

What does the resolve-todo tool do? +

Mark a claimed todo as completed/resolved. The todo is removed from the active task list. It is categorised as a Write tool in the Mmc 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-todo? +

Register the Mmc MCP server in PolicyLayer and add a rule for resolve-todo: 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 Mmc. Nothing to install.

What risk level is resolve-todo? +

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

Can I rate-limit resolve-todo? +

Yes. Add a rate_limit block to the resolve-todo 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-todo completely? +

Set action: deny in the PolicyLayer policy for resolve-todo. 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-todo? +

resolve-todo is provided by the Mmc MCP server (modelmycontext/mmc-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.