AI agents invoke cohere_chat 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 | — | Model ID (default: command-r-plus) |
api_key | string | — | Cohere API key |
message | string | Yes | User message |
preamble | string | — | System prompt / preamble |
max_tokens | number | — | |
temperature | number | — | |
chat_history | string | — | JSON array of prior messages [{role, message}] |
Parameters from the server's own tool schema.
This tool triggers an external API call to Cohere's LLM service, executing model inference with user-supplied prompts. It is an external operation whose effects depend on arguments (prompt injection risks, data exfiltration via crafted inputs). It goes beyond a simple Read as it sends data to a third-party service and can produce consequential outputs. Classified as Execute due to triggering external operations.
From the tool's definition 'Chat with a Cohere Command model. Supports system preamble and conversation history.'
Risk signalsHandles credentials or secrets (api_key)
Attacks that exploit this kind of access
Chat with a Cohere Command model. Supports system preamble and conversation history. 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_chat accepts 7 parameters: model, api_key, message, preamble, max_tokens, temperature, chat_history. Required: message. 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_chat: 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_chat 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_chat 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_chat. 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_chat 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 →