Drain leaves with extraction_status='pending' through the LLM extractor.
AI agents invoke files_extract_pending to trigger actions in M3 Memory. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers an active pipeline operation — running pending items through an LLM extractor — which constitutes executing an external process/operation rather than a simple read or write. It processes data through an AI model, which can have side effects on stored records (updating extraction status, modifying corpus state). 'Drain' implies consuming and transforming a queue, making it more than a passive read.
From the tool's definition 'Drain leaves with extraction_status=\'pending\' through the LLM extractor'
Documented attack patterns abuse exactly the kind of access files_extract_pending 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_extract_pending:
{
"version": "1",
"default": "deny",
"tools": {
"files_extract_pending": {
"limits": [
{
"counter": "files_extract_pending_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}files_extract_pending stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Drain leaves with extraction_status='pending' through the LLM extractor. It is categorised as a Execute tool in the M3 Memory MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the M3 Memory MCP server in PolicyLayer and add a rule for files_extract_pending: 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_extract_pending is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the files_extract_pending 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_extract_pending. 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_extract_pending 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.