AI agents use add_task to create or update resources in Mcp Tasks — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Tasks environment.
This tool creates a new record in the local SQLite database without deleting or overwriting existing data. The effect is reversible (tasks can be deleted), and there are no side effects outside the task tracker or financial implications. It is a straightforward Write operation with minimal blast radius—a misused agent would simply create unwanted tasks, which can be cleaned up.
From the tool's definition Tool name 'add_task' and description 'Insert a new task' indicate data creation. The action is reversible via delete_task.
Attacks that exploit this kind of access
Insert a new task. Returns the new task. It is categorised as a Write tool in the Mcp Tasks MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Tasks MCP server in PolicyLayer and add a rule for add_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 Mcp Tasks. Nothing to install.
add_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 add_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 add_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.
add_task is provided by the Mcp Tasks MCP server (kanaparthikiran/mcp-tasks-server). 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 →