AI agents call recall to retrieve information from Engram without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The recall tool queries stored data using multiple search strategies but does not create, modify, delete, or execute any operations. It retrieves information only. The blast radius of misuse is minimal—an agent could extract unwanted facts from memory, but cannot alter the underlying knowledge base or trigger side effects. This is a straightforward Read operation.
From the tool's definition Tool performs 'Search memory for relevant facts and observations' with 'semantic + keyword + temporal search' — a pure retrieval operation with no modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Search memory for relevant facts and observations. Uses semantic + keyword + temporal search with rank fusion. It is categorised as a Read tool in the Engram MCP Server, which means it retrieves data without modifying state.
Register the Engram 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 Engram. 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 Engram MCP server (reallyartificial/engram). 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 →