Medium Risk

set_task_tags

Set tags for a task (replaces existing tags). Args: task_id: ID of the task tags: New list of tags Returns: Updated task info with new tags

How to control set_task_tags ↓

What set_task_tags does on Taskdog

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

Medium Risk

Why set_task_tags needs a policy

This tool modifies task metadata (tags) rather than creating new tasks or destroying data. It qualifies as Write because it updates/replaces existing data reversibly. Severity is medium because incorrect tag changes could affect task organization and filtering, but tags are typically non-critical metadata compared to task content or dependencies.

From the tool's definition Tool description explicitly states it 'Set tags for a task (replaces existing tags)' - a modification operation that updates existing task data. The operation is reversible by calling the tool again with different tags.

Documented attack patterns abuse exactly the kind of access set_task_tags gives an agent:

How to control set_task_tags

PolicyLayer is an MCP gateway — it sits between your AI agents and Taskdog, and nothing reaches the server without passing your rules. This is the rule we recommend for set_task_tags:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "set_task_tags": {
      "limits": [
        {
          "counter": "set_task_tags_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

set_task_tags 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.

  1. Create a free account and register Taskdog — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about set_task_tags

What does the set_task_tags tool do? +

Set tags for a task (replaces existing tags). Args: task_id: ID of the task tags: New list of tags Returns: Updated task info with new tags. It is categorised as a Write tool in the Taskdog MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on set_task_tags? +

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

What risk level is set_task_tags? +

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

Can I rate-limit set_task_tags? +

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

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

set_task_tags is provided by the Taskdog MCP server (kohei-wada/taskdog). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Taskdog tool call.

Start from Taskdog, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

26 Taskdog tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.