Hybrid FTS5 + vector search over leaves.
AI agents call files_search 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.
This tool retrieves or queries data from the memory layer without side effects. It performs hybrid full-text and vector search, which are read-only operations. No data is created, modified, deleted, or used to trigger external operations. The low severity reflects minimal blast radius if misused — worst case is information disclosure of what the agent has stored, but no destructive or financial impact.
From the tool's definition Tool description states 'Hybrid FTS5 + vector search over leaves' — a search operation with no modification or deletion capability. The verb 'search' and the technical implementation (FTS5 full-text search, vector search) both indicate data retrieval only.
Documented attack patterns abuse exactly the kind of access files_search 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_search:
{
"version": "1",
"default": "deny",
"tools": {
"files_search": {}
}
}files_search 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.
Hybrid FTS5 + vector search over leaves. 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_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 M3 Memory. Nothing to install.
files_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 files_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 files_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.
files_search 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.