AI agents call get_related_deep 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 tool reads and traverses memory graph relationships without creating, modifying, or deleting any data. It follows existing links to retrieve related information, making it a pure Read operation. The presence of sibling tools like delete_memories and delete_memory confirms that destructive operations are separated and not part of this traversal function.
From the tool's definition Traversal multi-hop del grafo de memorias. Sigue enlaces salientes desde una memoria de origen - the tool performs graph traversal and follows outgoing links from a source memory, which are read-only operations with no modification or deletion capabilities.
Attacks that exploit this kind of access
Traversal multi-hop del grafo de memorias. Sigue enlaces salientes desde una memoria de origen. 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 get_related_deep: 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.
get_related_deep 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 get_related_deep 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 get_related_deep. 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.
get_related_deep is provided by the Engram MCP server (jacksini/engram-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 →