AI agents use vikunja_create_label to create or update resources in Vikunja — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Vikunja environment.
Creating a new label is a reversible Write operation—it adds data to the system without permanent destruction or code execution. The impact is limited to label metadata creation within a task management context. Severity is medium because uncontrolled label creation could clutter the system or be used to spam/manipulate task organization, but the operation is straightforward and reversible (labels can be deleted).
From the tool's definition Tool name 'vikunja_create_label' and description 'Create a new label' indicate creation of new data in the Vikunja task management system.
Attacks that exploit this kind of access
Create a new label. It is categorised as a Write tool in the Vikunja MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Vikunja MCP server in PolicyLayer and add a rule for vikunja_create_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. Nothing to install.
vikunja_create_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 vikunja_create_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 vikunja_create_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.
vikunja_create_label is provided by the Vikunja MCP server (shichao402/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 →