approve_task
AI agents use approve_task to create or update resources in Tendem MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tendem MCP environment.
The tool appears to approve a task, transitioning its state from pending/awaiting-approval to approved. This is a data modification (Write category) that is reversible—tasks can presumably be un-approved or re-evaluated. Without a description, confidence is moderate (0.65).
From the tool's definition Tool named 'approve_task' with empty description. The name indicates it modifies task state (approval status) in a task management system, constituting a reversible write operation.
Attacks that exploit this kind of access
approve_task. It is categorised as a Write tool in the Tendem MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tendem MCP server in PolicyLayer and add a rule for approve_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 Tendem MCP. Nothing to install.
approve_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 approve_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 approve_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.
approve_task is provided by the Tendem MCP server (toloka/tendem-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.