View available Perplexity models and their specializations, or manually override model selection. By default, models are auto-selected based on query intent (research, reasoning, general search).
AI agents call model_info to retrieve information from Perplexity MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about available models and their characteristics without modifying data, executing external operations, or causing side effects. The manual override feature is a read-level query parameter selection, not a destructive or executable action. It fits the Read category: retrieves or queries data with no side effects.
From the tool's definition Tool description states it enables viewing ("View available Perplexity models") and checking model information and specializations. The override capability is a configuration selection, not data modification or code execution.
Attacks that exploit this kind of access
View available Perplexity models and their specializations, or manually override model selection. By default, models are auto-selected based on query intent (research, reasoning, general search). It is categorised as a Read tool in the Perplexity MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Perplexity MCP Server MCP server in PolicyLayer and add a rule for model_info: 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 Perplexity MCP Server. Nothing to install.
model_info is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the model_info 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 model_info. 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.
model_info is provided by the Perplexity MCP Server MCP server (rossh121/perplexity-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
model_info is one line of Perplexity MCP Server's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →