Confirm which action items from a just-summarized session to convert into Crow notifications.
AI agents use crow_glasses_confirm_action_items to create or update resources in Crow — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Crow environment.
This tool creates/converts action items into Crow notifications, which is a write operation that persists new notification data. It is reversible in nature (notifications can typically be deleted), so it falls under Write rather than Destructive. Misuse could result in spurious notifications or unwanted tasks being created, giving it medium severity.
From the tool's definition 'Confirm which action items from a just-summarized session to convert into Crow notifications'
Documented attack patterns abuse exactly the kind of access crow_glasses_confirm_action_items gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Crow, and nothing reaches the server without passing your rules. This is the rule we recommend for crow_glasses_confirm_action_items:
{
"version": "1",
"default": "deny",
"tools": {
"crow_glasses_confirm_action_items": {
"limits": [
{
"counter": "crow_glasses_confirm_action_items_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} crow_glasses_confirm_action_items stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Confirm which action items from a just-summarized session to convert into Crow notifications. It is categorised as a Write tool in the Crow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Crow MCP server in PolicyLayer and add a rule for crow_glasses_confirm_action_items: 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_glasses_confirm_action_items 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 crow_glasses_confirm_action_items 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_glasses_confirm_action_items. 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_glasses_confirm_action_items 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.
Start from Crow, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
576 Crow tools catalogued and risk-classified — across an index of 43,000+ MCP servers.