AI agents call rerank to retrieve information from Litellm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Reranking is a read/query operation that scores and orders existing documents based on relevance to a query. It retrieves relevance scores without creating, modifying, or deleting any data, and has no side effects beyond returning ranked results.
From the tool's definition Rerank documents based on a query using LiteLLM (/rerank)
Attacks that exploit this kind of access
Rerank documents based on a query using LiteLLM (/rerank). It is categorised as a Read tool in the Litellm MCP Server, which means it retrieves data without modifying state.
Register the Litellm MCP server in PolicyLayer and add a rule for rerank: 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 Litellm. Nothing to install.
rerank 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 rerank 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 rerank. 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.
rerank is provided by the Litellm MCP server (litellm-mcp-server). 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 →