AI agents invoke anthropic_create_message 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 | — | Claude model ID (default: claude-sonnet-4-6) |
top_k | number | — | |
top_p | number | — | |
prompt | string | — | Convenience: single user message (alternative to messages array) |
system | string | — | System prompt |
api_key | string | Yes | |
messages | object | — | Array of {role, content} message objects |
max_tokens | number | — | Max tokens to generate (default: 1024) |
temperature | number | — | |
stop_sequences | object | — | Array of stop sequences |
Parameters from the server's own tool schema.
This tool triggers an external API call to Anthropic's Claude models, executing LLM inference with arbitrary inputs. It spans Execute territory because it runs an external operation whose effects depend on the arguments passed.
From the tool's definition "Send a message to the Anthropic Messages API" and "agents that need to call Claude programmatically"
Risk signalsHandles credentials or secrets (api_key) · High parameter count (10 properties)
Attacks that exploit this kind of access
Send a message to the Anthropic Messages API (Claude models). Useful for agents that need to call Claude programmatically or compare model outputs. 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.
anthropic_create_message accepts 10 parameters: model, top_k, top_p, prompt, system, api_key, messages, max_tokens, temperature, stop_sequences. 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 anthropic_create_message: 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.
anthropic_create_message 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 anthropic_create_message 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 anthropic_create_message. 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.
anthropic_create_message 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 →