AI agents invoke run_extraction to trigger actions in Sifter. 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 extraction process on documents, which is an operation with side effects (creates/modifies records in the sift). It does not merely read data (would be Read), nor does it delete data (would be Destructive). The 'enqueue extraction' framing indicates it initiates a computational process rather than a simple query.
From the tool's definition Tool name 'run_extraction' indicates it enqueues/triggers an external operation (document extraction). The server description emphasizes transformation of documents into structured records, which involves executing a processing pipeline whose effects depend…
Documented attack patterns abuse exactly the kind of access run_extraction gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Sifter, and nothing reaches the server without passing your rules. This is the rule we recommend for run_extraction:
{
"version": "1",
"default": "deny",
"tools": {
"run_extraction": {
"limits": [
{
"counter": "run_extraction_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_extraction 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.
Enqueue extraction for a document on a specific sift. It is categorised as a Execute tool in the Sifter MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Sifter MCP server in PolicyLayer and add a rule for run_extraction: 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 Sifter. Nothing to install.
run_extraction 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 run_extraction 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 run_extraction. 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.
run_extraction is provided by the Sifter MCP server (sifter-ai/sifter). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 15 Sifter tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
15 Sifter tools catalogued and risk-classified — across an index of 42,500+ MCP servers.