perplexity_medium
AI agents call perplexity_medium 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 is part of Perplexity AI's search-enhanced query system. Based on the server's stated purpose and the absence of any mutative, destructive, or executable capabilities in the description, this tool performs information retrieval and analysis—a Read operation.
From the tool's definition Tool named 'perplexity_medium' is described as part of a server providing 'search-enhanced language models' with different 'complexity levels for quick fact-checking, technical analysis, and deep research.' No mutation, deletion, execution, or financial…
Attacks that exploit this kind of access
perplexity_medium. 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 perplexity_medium: 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.
perplexity_medium 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 perplexity_medium 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_medium. 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_medium is provided by the Perplexity MCP Server MCP server (rohit-seelam/perplexity_mcp). 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 →