AI agents call mem_recall to retrieve information from Crossmem without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Given the server's stated purpose of enabling AI assistants to 'recall' cross-project knowledge, and the semantic meaning of 'recall' as retrieval, this tool almost certainly queries or fetches stored memory data. The empty description prevents higher confidence, but the naming convention and functional context strongly indicate a Read operation with no side effects.
From the tool's definition Tool name 'mem_recall' strongly suggests retrieval of stored memories. Sibling tools include 'mem_search' (clearly Read), 'mem_save' and 'mem_ingest' (Write), and 'mem_forget' (Destructive), establishing a pattern where 'recall' retrieves data without…
Attacks that exploit this kind of access
mem_recall. It is categorised as a Read tool in the Crossmem MCP Server, which means it retrieves data without modifying state.
Register the Crossmem MCP server in PolicyLayer and add a rule for mem_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 Crossmem. Nothing to install.
mem_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 mem_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 mem_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.
mem_recall is provided by the Crossmem MCP server (jamiemoles/crossmem). 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 →