Analyze memory health: find stale, contradictory, or redundant memories. Returns a consolidation report without making changes. Use with the /crow-dream skill for the full workflow.
AI agents call crow_dream 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 tool performs pure analysis and reporting on existing memory data. It queries the memory system to identify issues but does not execute any modifications, deletions, or external operations. The consolidation report is informational output, not a command for action. This is a straightforward Read operation.
From the tool's definition The tool 'find stale, contradictory, or redundant memories' and 'Returns a consolidation report without making changes' indicates it retrieves and analyzes data without modifying or deleting anything.
Documented attack patterns abuse exactly the kind of access crow_dream 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_dream:
{
"version": "1",
"default": "deny",
"tools": {
"crow_dream": {}
}
}crow_dream 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.
Analyze memory health: find stale, contradictory, or redundant memories. Returns a consolidation report without making changes. Use with the /crow-dream skill for the full workflow. 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_dream: 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_dream 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_dream 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_dream. 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_dream 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.