AI agents use vikunja_update_project 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.
This tool creates or modifies data reversibly by updating an existing project's properties (name, description, settings, etc.). Updates can be undone by changing the values back, placing it squarely in the Write category.
From the tool's definition Tool name 'vikunja_update_project' and description 'Update an existing Vikunja project' indicate modification of data. The operation modifies project metadata or state but does not create new entities or irreversibly delete data.
Attacks that exploit this kind of access
Update an existing Vikunja project. 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_update_project: 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_update_project 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_update_project 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_update_project. 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_update_project 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 →