AI agents call find_duplicates 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 analyzes existing session data using embedding similarity comparison to identify duplicates. It is purely a read operation that queries the memory system without creating, modifying, or deleting any data. The output is informational—a list of similar session pairs—with no capability to alter state.
From the tool's definition Tool 'find_duplicates' performs a search/query operation: 'Find duplicate or near-duplicate sessions using embedding similarity.
Attacks that exploit this kind of access
Find duplicate or near-duplicate sessions using embedding similarity. Returns pairs of sessions above the similarity threshold. 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 find_duplicates: 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.
find_duplicates 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 find_duplicates 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 find_duplicates. 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.
find_duplicates 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 →