AI agents call cohere_rerank to retrieve information from UnClick without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | — | Rerank model (default: rerank-english-v3.0) |
query | string | Yes | |
top_n | number | — | Return top N results |
api_key | string | — | |
documents | string | Yes | JSON array of strings or {text} objects |
Parameters from the server's own tool schema.
This tool performs information retrieval and ranking, which is a read-only operation. It does not create, modify, delete, or execute any data — it only reorders existing documents based on relevance scoring. The blast radius of misuse is minimal: at worst, an agent receives poorly-ranked search results, with no side effects on data or external systems.
From the tool's definition Tool description states 'Rerank a list of documents by relevance to a query' — this is a retrieval/ranking operation with no modification, deletion, or execution of external commands. It takes documents and a query as inputs and returns a reranked list.
Risk signalsAccepts freeform code/query input (query) · Handles credentials or secrets (api_key)
Attacks that exploit this kind of access
Rerank a list of documents by relevance to a query using Cohere Rerank. It is categorised as a Read tool in the UnClick MCP Server, which means it retrieves data without modifying state.
cohere_rerank accepts 5 parameters: model, query, top_n, api_key, documents. Required: query, documents. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for cohere_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 UnClick. Nothing to install.
cohere_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 cohere_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 cohere_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.
cohere_rerank is provided by the UnClick MCP server (@unclick/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 →