Add a label to a task
AI agents use add_task_label to create or update resources in Vikunja MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Vikunja MCP Server environment.
Adding a label modifies task metadata in a way that can be undone (by removing the label). This is a Write operation rather than Read (it changes state), Execute (it doesn't run code or trigger external logic), Destructive (it's reversible), or Financial (no money involved). The blast radius is minimal since label changes don't affect critical task data or other systems.
From the tool's definition Tool name 'add_task_label' and description 'Add a label to a task' indicate a label is being added to an existing task. This is a reversible modification operation (labels can be removed).
Attacks that exploit this kind of access
Add a label to a task. It is categorised as a Write tool in the Vikunja MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Vikunja MCP Server MCP server in PolicyLayer and add a rule for add_task_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 Vikunja MCP Server. Nothing to install.
add_task_label is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_task_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.
Set action: deny in the PolicyLayer policy for add_task_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.
add_task_label is provided by the Vikunja MCP Server MCP server (wosh-i/vikunja-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →