Low Risk

query_sift

Run a natural language query over a sift's extracted records.

How to control query_sift ↓

AI agents call query_sift to retrieve information from Sifter without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

This tool retrieves or searches data from already-extracted records using natural language queries. It has no side effects—it does not create, modify, delete, or execute external operations. The sibling tools (create_sift, delete_sift, aggregate_sift) handle mutations; this tool is explicitly a query operation, fitting squarely in the Read category.

From the tool's definition Tool description states: 'Run a natural language query over a sift's extracted records.' The verb 'query' and 'run...over' indicate read-only retrieval of data without modification. No language suggests mutation, deletion, or execution of arbitrary code.

Documented attack patterns abuse exactly the kind of access query_sift 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 query_sift:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "query_sift": {}
  }
}

query_sift is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Sifter — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Go deeper

What does the query_sift tool do? +

Run a natural language query over a sift's extracted records. It is categorised as a Read tool in the Sifter MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on query_sift? +

Register the Sifter MCP server in PolicyLayer and add a rule for query_sift: 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.

What risk level is query_sift? +

query_sift is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit query_sift? +

Yes. Add a rate_limit block to the query_sift 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.

How do I block query_sift completely? +

Set action: deny in the PolicyLayer policy for query_sift. 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.

What MCP server provides query_sift? +

query_sift 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.

Enforce policy on every Sifter tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.