AI agents use task_add to create or update resources in Recap — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Recap environment.
This tool creates new task records in the project's persistent markdown storage. While reversible (tasks can be deleted via task_delete or edited via task_update), it modifies the project state and could accumulate unwanted tasks if misused by an AI agent. Severity is medium because the blast radius is limited to a local workspace and changes are reversible, though data clutter and workflow disruption are possible.
From the tool's definition Tool description states 'Add a task to a project', indicating creation of new data. The sibling tool 'task_delete' and structured parameters (priority, due date, notes) confirm this is a data-creation operation stored in the markdown workspace.
Attacks that exploit this kind of access
Add a task to a project. Supports priority, due date, and notes. It is categorised as a Write tool in the Recap MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Recap MCP server in PolicyLayer and add a rule for task_add: 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 Recap. Nothing to install.
task_add 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 task_add 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 task_add. 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.
task_add is provided by the Recap MCP server (shivam-singh-git/recap-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 →