AI agents invoke cohere_classify to trigger actions in UnClick. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | — | |
inputs | string | Yes | JSON array of strings to classify |
api_key | string | — | |
examples | string | Yes | JSON array of {text, label} few-shot examples |
Parameters from the server's own tool schema.
This tool sends text data to an external AI service (Cohere) to perform classification. It triggers an external API call whose effects depend on the input arguments, placing it in the Execute category. The blast radius is medium — it involves sending potentially sensitive text to a third-party AI provider, but does not modify, delete, or move financial resources.
From the tool's definition Classify texts into categories using Cohere Classify with few-shot examples
Risk signalsHandles credentials or secrets (api_key)
Attacks that exploit this kind of access
Classify texts into categories using Cohere Classify with few-shot examples. It is categorised as a Execute tool in the UnClick MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
cohere_classify accepts 4 parameters: model, inputs, api_key, examples. Required: inputs, examples. 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_classify: 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_classify is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the cohere_classify 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_classify. 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_classify 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 →