AI agents use create_task to create or update resources in Zakar — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zakar environment.
This tool creates new task entries in the Zakar memory platform and establishes project relationships. These are Write operations because they create/modify data, but are reversible (tasks can be deleted or modified later).
From the tool's definition Tool name is 'create_task' and description states it 'Create a curated task' and 'Link it to a project' — these are create and link operations that modify data reversibly in the memory system.
Attacks that exploit this kind of access
Create a curated task (open_brain_tasks). Link it to a project by slug or name so it lands in that project. It is categorised as a Write tool in the Zakar MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Zakar MCP server in PolicyLayer and add a rule for create_task: 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 Zakar. Nothing to install.
create_task 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 create_task 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 create_task. 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.
create_task is provided by the Zakar MCP server (tkbrannon/zakar). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
create_task is one line of Zakar's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →