unblock_task
AI agents use unblock_task to create or update resources in Keshro MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Keshro MCP environment.
Unblocking a task modifies task metadata/state reversibly (a blocked task can be blocked again), placing it in Write rather than Execute or Destructive. The empty description reduces confidence. Medium severity reflects potential workflow disruption if an agent unblocks critical tasks inappropriately, but the effect is reversible.
From the tool's definition Tool name 'unblock_task' indicates modification of task state; description is empty, limiting certainty. Sibling tools like 'block_task', 'complete_task', 'edit_task' suggest this server manages task workflow state reversibly.
Attacks that exploit this kind of access
unblock_task. It is categorised as a Write tool in the Keshro MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Keshro MCP server in PolicyLayer and add a rule for unblock_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 Keshro MCP. Nothing to install.
unblock_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 unblock_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 unblock_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.
unblock_task is provided by the Keshro MCP server (jlewitt1/keshro-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 →