Block a task pending human approval.
AI agents use mark_task_blocked_human to create or update resources in Dag Planner — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Dag Planner environment.
This tool modifies task state by marking it as blocked, which is a reversible write operation. It does not execute code, delete data, or move funds. The blocking state can be unblocked or the task re-evaluated, making it a Write rather than Destructive action.
From the tool's definition Tool name 'mark_task_blocked_human' and description 'Block a task pending human approval' indicate state modification of an existing task record.
Attacks that exploit this kind of access
Block a task pending human approval. It is categorised as a Write tool in the Dag Planner MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Dag Planner MCP server in PolicyLayer and add a rule for mark_task_blocked_human: 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 Dag Planner. Nothing to install.
mark_task_blocked_human 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 mark_task_blocked_human 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 mark_task_blocked_human. 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.
mark_task_blocked_human is provided by the Dag Planner MCP server (shubhamnegi/dag-planner-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 →