AI agents call recall to retrieve information from Memmd without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a shared memory store and returns matching entries. It has read-only semantics with no side effects, reversible operations, code execution, data destruction, or financial impact. The blast radius of misuse is minimal—an agent could retrieve sensitive information stored in memory, but cannot modify, delete, or act on it directly.
From the tool's definition 'Search memory entries' indicates retrieval of data without modification. The tool supports optional filtering by 'section/category' but performs no write, delete, or execution operations.
Attacks that exploit this kind of access
Search memory entries with optional section/category filters. It is categorised as a Read tool in the Memmd MCP Server, which means it retrieves data without modifying state.
Register the Memmd MCP server in PolicyLayer and add a rule for 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 Memmd. Nothing to install.
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 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 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.
recall is provided by the Memmd MCP server (matamong/memmd-mcp). 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 →