AI agents invoke groq_chat_completion 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 |
|---|---|---|---|
stop | object | — | Stop sequence(s) |
model | string | — | Model ID (e.g. llama-3.3-70b-versatile, mixtral-8x7b-32768, gemma2-9b-it). Default: llama-3.3-70b-versatile |
top_p | number | — | Top-p sampling (0-1) |
prompt | string | — | Single user message (alternative to messages) |
api_key | string | Yes | Groq API key from console.groq.com/keys |
messages | array | — | Array of {role, content} messages |
max_tokens | number | — | Maximum tokens to generate |
temperature | number | — | Sampling temperature (0-2) |
system_prompt | string | — | System prompt (used with prompt shorthand) |
Parameters from the server's own tool schema.
Executing arbitrary LLM inference with user-supplied prompts is an Execute operation—the tool triggers external computational services whose effects (responses, side effects via the model) depend on the arguments provided.
From the tool's definition Tool runs LLM inference ("Run a fast LLM inference with Groq"), which executes an external service and produces outputs dependent on arbitrary input prompts. This is a code/computation execution operation.
Risk signalsHandles credentials or secrets (api_key)
Attacks that exploit this kind of access
Run a fast LLM inference with Groq. Supports Llama 3, Mixtral, Gemma, and other open models at high speed. 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.
groq_chat_completion accepts 9 parameters: stop, model, top_p, prompt, api_key, messages, max_tokens, temperature, system_prompt. Required: api_key. 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 groq_chat_completion: 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.
groq_chat_completion 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 groq_chat_completion 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 groq_chat_completion. 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.
groq_chat_completion 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 →