Proactive recall: search ALL knowledge sources (memories, research sources, research notes, blog posts) for topic-relevant context. Use before writing, creating content, or analyzing to pull in findings from prior sessions.
AI agents call crow_deep_recall to retrieve information from Crow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is fundamentally a Read operation as it retrieves and queries data from multiple knowledge sources without creating, modifying, or deleting anything. Severity is elevated to high due to the comprehensive scope ("ALL knowledge sources") and potential sensitivity of the data being accessed, including private memories and research notes that could contain confidential project information, credentials, or personal…
From the tool's definition Tool performs "search ALL knowledge sources (memories, research sources, research notes, blog posts) for topic-relevant context" — a retrieval operation across persistent memory and stored data without modification.
Documented attack patterns abuse exactly the kind of access crow_deep_recall 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_deep_recall:
{
"version": "1",
"default": "deny",
"tools": {
"crow_deep_recall": {}
}
}crow_deep_recall is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Proactive recall: search ALL knowledge sources (memories, research sources, research notes, blog posts) for topic-relevant context. Use before writing, creating content, or analyzing to pull in findings from prior sessions. It is categorised as a Read tool in the Crow MCP Server, which means it retrieves data without modifying state.
Register the Crow MCP server in PolicyLayer and add a rule for crow_deep_recall: 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_deep_recall is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the crow_deep_recall 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_deep_recall. 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_deep_recall 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.