Scan leaf embeddings for near-duplicates. Detection only —
AI agents call files_dedup to retrieve information from M3 Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
files_dedup performs analysis and detection of duplicate data without creating, modifying, deleting, or executing any operations. The 'Detection only' qualifier confirms this is a non-destructive informational tool. The severity is low because even if misused, it cannot alter data or trigger external operations—it merely reports findings.
From the tool's definition Tool description explicitly states 'Detection only' and the operation is a scan of embeddings to identify near-duplicates, which is a read-only analysis operation with no side effects or modifications.
Documented attack patterns abuse exactly the kind of access files_dedup gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and M3 Memory, and nothing reaches the server without passing your rules. This is the rule we recommend for files_dedup:
{
"version": "1",
"default": "deny",
"tools": {
"files_dedup": {}
}
}files_dedup is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Scan leaf embeddings for near-duplicates. Detection only —. It is categorised as a Read tool in the M3 Memory MCP Server, which means it retrieves data without modifying state.
Register the M3 Memory MCP server in PolicyLayer and add a rule for files_dedup: 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 M3 Memory. Nothing to install.
files_dedup 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 files_dedup 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 files_dedup. 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.
files_dedup is provided by the M3 Memory MCP server (skynetcmd/m3-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from M3 Memory, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
43 M3 Memory tools catalogued and risk-classified — across an index of 43,000+ MCP servers.