mistral_chat_completion

Run a chat completion with a Mistral AI model (mistral-small, mistral-medium, mistral-large, etc.).

Server UnClick @unclick/mcp-server
Category Execute
Risk class High
Parameters 80 required

What mistral_chat_completion does on UnClick

AI agents invoke mistral_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.

ParameterTypeRequiredDescription
model string Model ID (default: mistral-small-latest)
top_p number
prompt string Single user message (alternative to messages)
api_key string Mistral API key
messages string JSON array of {role, content} messages
max_tokens number
temperature number
system_prompt string

Parameters from the server's own tool schema.

Why mistral_chat_completion needs a policy

This is an Execute category tool because it triggers execution of external code/operations (a remote AI model inference) whose side effects and output depend entirely on the arguments provided. It is not Read (it does not merely retrieve data), Write (it does not persist data), Destructive (it does not delete/overwrite), Financial (no money moves), or Other.

From the tool's definition The tool description explicitly states 'Run a chat completion with a Mistral AI model', indicating execution of an external AI service with model-dependent behavior.

Risk signalsHandles credentials or secrets (api_key)

Questions about mistral_chat_completion

What does the mistral_chat_completion tool do? +

Run a chat completion with a Mistral AI model (mistral-small, mistral-medium, mistral-large, etc.). 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.

What parameters does mistral_chat_completion accept? +

mistral_chat_completion accepts 8 parameters: model, top_p, prompt, api_key, messages, max_tokens, temperature, system_prompt. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on mistral_chat_completion? +

Register the UnClick MCP server in PolicyLayer and add a rule for mistral_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.

What risk level is mistral_chat_completion? +

mistral_chat_completion is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit mistral_chat_completion? +

Yes. Add a rate_limit block to the mistral_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.

How do I block mistral_chat_completion completely? +

Set action: deny in the PolicyLayer policy for mistral_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.

What MCP server provides mistral_chat_completion? +

mistral_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.

// 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.