AI agents call neural_search 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.
This tool retrieves and queries data from persistent memory indexed by semantic meaning. It has no side effects—it does not create, modify, delete, or execute anything. It is purely a read operation that helps AI agents discover information from prior sessions. The low severity reflects that misuse would only expose information already belonging to the user, with no destructive or operational consequences.
From the tool's definition Tool performs 'semantic search across all Engram sessions' to 'find relevant past work, learnings, and context.' The verb 'search' and 'find' indicate retrieval without modification. No creation, deletion, execution, or financial operations are described.
Attacks that exploit this kind of access
Semantic search across all Engram sessions. Finds sessions by meaning, not just keywords. Use this to find relevant past work, learnings, and context. 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 neural_search: 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.
neural_search 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 neural_search 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 neural_search. 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.
neural_search is provided by the Engram MCP server (tinydarkforge/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 →