AI agents call score_snippets to retrieve information from Nesift without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that evaluates and ranks existing text data. It retrieves or processes information (snippet relevance scores) without creating, modifying, deleting, or executing anything. The explicit note 'without fetching' further confirms it performs no external operations. Severity is low because misuse would only return ranked results, with no ability to damage data or systems.
From the tool's definition Tool 'scores snippets by semantic relevance to a query, without fetching' - performs ranking/scoring of already-retrieved text snippets with no data modification, deletion, execution, or side effects.
Attacks that exploit this kind of access
Rank text snippets by semantic relevance to a query, without fetching. It is categorised as a Read tool in the Nesift MCP Server, which means it retrieves data without modifying state.
Register the Nesift MCP server in PolicyLayer and add a rule for score_snippets: 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 Nesift. Nothing to install.
score_snippets 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 score_snippets 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 score_snippets. 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.
score_snippets is provided by the Nesift MCP server (scottgl9/nesift). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →