add_label · Todoist MCP: Risk & Policy

WHAT IT DOES

What add_label does on Todoist

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

WHY IT NEEDS A POLICY

Why add_label needs a policy

This tool creates a label within Todoist, which is a reversible operation. Labels can be deleted or modified later (as evidenced by the 'delete_label' sibling tool). No destructive, financial, or code execution capability is implied. This is a straightforward data creation operation with low blast radius if misused by an AI agent.

From the tool's definition Tool name 'add_label' explicitly indicates creating a new label. Sibling tools like 'create_task', 'add_project', 'add_section', and 'add_comment' all perform Write operations (reversible creation), and 'add_label' follows the same pattern.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_label Rate-limited

add_label 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": {
    "add_label": {
      "limits": [
        {
          "counter": "add_label_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 Todoist, so you can run agents against it safely.

FAQ

Questions about add_label

What does the add_label tool do? +

add_label. It is categorised as a Write tool in the Todoist MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_label? +

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

What risk level is add_label? +

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

Can I rate-limit add_label? +

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

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

add_label is provided by the Todoist MCP server (stevengonsalvez/mcp-todoist). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.