crow_delegate
Hand off a LONG or BACKGROUND task to be done asynchronously by a Crow bot, returning
This record as markdown: /tools/kh0pper-crow/crow-delegate.md
What crow_delegate does on Crow
AI agents invoke crow_delegate to trigger actions in Crow. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why crow_delegate is rated High
This tool delegates tasks to an autonomous bot for asynchronous execution. The actual effects depend entirely on what task is handed off, which could range from benign reads to destructive operations. Since it executes arbitrary background tasks via an external agent, Execute is the most appropriate base category.
From the tool's definition "Hand off a LONG or BACKGROUND task to be done asynchronously by a Crow bot" — triggers external autonomous agent execution
Attacks that exploit this kind of access
The rule that runs crow_delegate safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Crow, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For crow_delegate, this is the rule to start with:
crow_delegate stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Crow, apply this rule, and every crow_delegate call is checked against it from then on.
Questions about crow_delegate
Hand off a LONG or BACKGROUND task to be done asynchronously by a Crow bot, returning. It is categorised as a Execute tool in the Crow MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Crow MCP server in PolicyLayer and add a rule for crow_delegate: 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 Crow. Nothing to install.
crow_delegate is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the crow_delegate 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 crow_delegate. 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.
crow_delegate is provided by the Crow MCP server (kh0pper/crow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Crow, and thousands of servers like it.
This server
Across the catalogue