AI agents invoke perplexity_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 |
|---|---|---|---|
model | string | — | Model (default: sonar). Options: sonar, sonar-pro, sonar-reasoning |
prompt | string | — | User message (alternative to messages) |
api_key | string | — | Perplexity API key |
messages | string | — | JSON array of {role, content} messages |
max_tokens | number | — | |
temperature | number | — | |
system_prompt | string | — | |
return_citations | boolean | — | Include citation URLs in response (default true) |
search_domain_filter | string | — | JSON array of domains to restrict search to |
search_recency_filter | string | — | Limit sources by time: month, week, day, hour |
return_related_questions | boolean | — |
Parameters from the server's own tool schema.
This tool executes a remote operation (calling Perplexity's API to run a chat completion with web search) rather than simply reading static data. While it appears safe in isolation (returns citations and grounded answers), it meets the Execute category because it: (1) triggers external operations whose effects depend on arguments (the search query), (2) makes real-time requests to an external service, and (3) could…
From the tool's definition Tool performs 'Run a search-augmented chat completion' with Perplexity AI, which executes an external AI operation.
Risk signalsHandles credentials or secrets (api_key) · High parameter count (11 properties)
Attacks that exploit this kind of access
Run a search-augmented chat completion with Perplexity AI. Returns grounded answers with citations from the web. 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.
perplexity_chat_completion accepts 11 parameters: model, prompt, api_key, messages, max_tokens, temperature, system_prompt, return_citations, search_domain_filter, search_recency_filter, return_related_questions. 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 perplexity_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.
perplexity_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 perplexity_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 perplexity_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.
perplexity_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 →