Close study · not a fake MCP listing
SKILL.md — Perplexity
Real skill file for agents. When to use / when not is inside the document. This is not a fake MCP listing.
File
Raw
--- name: perplexity description: Operate Perplexity as an agent using public APIs, CLIs, and docs. Twin Score agent 78. --- # Perplexity skill Perplexity is an answer engine that retrieves the live web and cites sources in the same breath as the prose. That citation habit is why humans use it for research instead of a naked chat model. Collections, Spaces, and the mobile apps are polished. The API exposes search and reasoning but is thinner than the consumer UI, so agents still often wrap the site rather than the official endpoint — a gap we record rather than pretend is closed. Twin Score on this directory is 85 for humans and 78 for agents, using the public rubric (interface, onboarding, human docs, collaboration, support, pricing fairness, accessibility, reliability versus API quality, MCP or tool surface, CLI, structured docs, machine auth, quotas, determinism, and skill packaging). Perplexity is sold by Perplexity AI, founded 2022, headquartered in San Francisco, USA. Pricing in public materials: Free search; Perplexity Pro and Enterprise with higher limits and model choice. Machine capabilities we record: API strong, MCP basic, CLI none, docs strong, auth Account plus API keys. This page is editorial, not a star rating scraped from users. ## When to use Use this skill when a user asks to integrate, script, or evaluate Perplexity (Perplexity AI). ## When not to use Do not claim an MCP server exists unless the capability matrix says so (current MCP level: basic). Do not invent user-count ratings. ## Capability matrix | Surface | Level | |---|---| | API | strong | | MCP | basic | | CLI | none | | Docs | strong | | Auth | Account plus API keys | | Webhooks | strong | | SDKs | http, python | ## Auth Account plus API keys ## Pricing (public) Free search; Perplexity Pro and Enterprise with higher limits and model choice. ## Official site https://www.perplexity.ai ## Twin Score Human 85. Agent 78. Updated 2026-08-01. Rubric: https://buildsomethingagentswant.com/scorecard ## Alternatives - chatgpt - gemini - claude