memory_recall
AI agents call memory_recall to retrieve information from Claude Crowed without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears designed to query or retrieve information from the persistent semantic memory store. Although the description is absent (lowering confidence slightly), the name 'recall' combined with the server's function as a 'structured document store' with 'semantic search' capabilities strongly suggests a read-only retrieval operation.
From the tool's definition Tool name is 'memory_recall' on a semantic memory system; sibling tools include 'memory_read', 'memory_history', and 'memory_related' which are all retrieval operations.
Attacks that exploit this kind of access
memory_recall. It is categorised as a Read tool in the Claude Crowed MCP Server, which means it retrieves data without modifying state.
Register the Claude Crowed MCP server in PolicyLayer and add a rule for memory_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 Claude Crowed. Nothing to install.
memory_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 memory_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 memory_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.
memory_recall is provided by the Claude Crowed MCP server (thenewjavaman/claude-crowed). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →