AI agents use add_task_file to create or update resources in Todos — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Todos environment.
This tool creates or updates associations between files and tasks (upsert operation), which is reversible data modification. It does not execute code, delete data, or move money. While it tracks file references and detects conflicts, the core action is writing metadata.
From the tool's definition Tool description states it 'Link[s] a file path to a task' and 'Upserts if same task+path exists', indicating creation or modification of task-file associations.
Attacks that exploit this kind of access
Link a file path to a task. Tracks which files an agent is working on. Upserts if same task+path exists. Auto-detects conflicts with other in-progress tasks. It is categorised as a Write tool in the Todos MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Todos MCP server in PolicyLayer and add a rule for add_task_file: 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 Todos. Nothing to install.
add_task_file 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_file 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_file. 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_file is provided by the Todos MCP server (@hasna/todos). 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 →