AI agents call recall_memory to retrieve information from Memlord without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
'Recall' typically means to retrieve or fetch stored information without modification. The tool fits alongside other Read operations (get_memory, retrieve_memory, list_memories, search_by_tag) on a memory server. Since it performs no modification, deletion, or execution, it is classified as Read with medium-high confidence. The empty description prevents higher confidence, but the pattern is clear.
From the tool's definition Tool name 'recall_memory' combined with sibling tools (get_memory, retrieve_memory, search_by_tag) suggests a data retrieval operation. The description is empty, so classification relies on naming convention and context.
Documented attack patterns abuse exactly the kind of access recall_memory gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Memlord, and nothing reaches the server without passing your rules. This is the rule we recommend for recall_memory:
{
"version": "1",
"default": "deny",
"tools": {
"recall_memory": {}
}
}recall_memory 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.
recall_memory. It is categorised as a Read tool in the Memlord MCP Server, which means it retrieves data without modifying state.
Register the Memlord MCP server in PolicyLayer and add a rule for recall_memory: 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 Memlord. Nothing to install.
recall_memory 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 recall_memory 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 recall_memory. 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.
recall_memory is provided by the Memlord MCP server (myrikld/memlord). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Memlord, 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.
10 Memlord tools catalogued and risk-classified — across an index of 43,000+ MCP servers.