block_task
AI agents use block_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.
Blocking a task reverses a task's active status without permanently deleting it, making it a reversible modification (Write) rather than destructive. Within a project management context for 'high-stakes engineering projects,' blocking tasks affects workflow state and could impact team coordination, warranting medium severity.
From the tool's definition Tool name 'block_task' suggests modification of task state. Server context shows task management operations (complete_task, edit_task, add_task) that are Write operations. Description is empty, limiting certainty.
Attacks that exploit this kind of access
block_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 block_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.
block_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 block_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 block_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.
block_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.
block_task is one line of Keshro's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →