update_todos · Prompts MCP: Risk & Policy

WHAT IT DOES

What update_todos does on Prompts

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

WHY IT NEEDS A POLICY

Why update_todos needs a policy

The update_todos tool modifies project documentation (todos.md) by changing task status or content. This is a Write operation—it creates or modifies data reversibly. While the impact is low in isolation (task tracking), misuse by an AI agent (e.g., marking critical tasks complete, removing project blockers) could misdirect human workflows.

From the tool's definition Tool updates todos.md with task items. Description indicates 'update' action on structured project data. From sibling tools context (add_rule, add_skill, init_prompts), this server manages persistent project state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_todos Rate-limited

update_todos 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": {
    "update_todos": {
      "limits": [
        {
          "counter": "update_todos_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 Prompts, so you can run agents against it safely.

FAQ

Questions about update_todos

What does the update_todos tool do? +

【更新待办】更新 todos.md 中的待办事项。. It is categorised as a Write tool in the Prompts MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on update_todos? +

Register the Prompts MCP server in PolicyLayer and add a rule for update_todos: 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 Prompts. Nothing to install.

What risk level is update_todos? +

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

Can I rate-limit update_todos? +

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

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

update_todos is provided by the Prompts MCP server (thana0623/pmcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.