rerank

Rerank documents based on a query using LiteLLM (/rerank)

Server Litellm litellm-mcp-server
Category Read
Risk class Low
Parameters 00 required

What rerank does on Litellm

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.

Why rerank needs a policy

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)

Questions about rerank

What does the rerank tool do? +

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.

How do I enforce a policy on rerank? +

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.

What risk level is rerank? +

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

Can I rate-limit rerank? +

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.

How do I block rerank completely? +

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.

What MCP server provides rerank? +

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.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.