This MCP server integrates Perplexity AI's Sonar models into coding assistants to provide specialized research and fact-checking capabilities through two focused tools:
lookup - Fetch precise, source-backed facts about API syntax, parameters, configuration keys, CLI flags, runtime compatibility, and package metadata without recommendations.
answer - Perform comprehensive research to compare libraries, evaluate architecture trade-offs, plan migrations, debug complex issues, and make performance decisions with actionable recommendations backed by official sources.
Key Features:
Context-efficient design using only ~1.3K tokens to preserve your AI assistant's context window
Automatic model selection:
sonar-profor quick lookups,sonar-reasoning-profor deep researchCoding-specialized system prompts tailored for technical decision-making and fact extraction
Provides access to Perplexity AI through two tools: lookup for quick fact-checking and research queries, and answer for in-depth research with recommendations and comparisons
Perplexity Agent MCP
An opinionated, coding-specialized, Model Context Protocol server that integrates Perplexity AI's Sonar models into AI coding assistants like Claude Code or Codex CLI. It's deliberately lean and adds very few tokens to your context. It provides two specialized tools—lookup for instant fact-checking of API syntax and documentation details, and answer for comprehensive research with actionable recommendations.
Setup
Install the published package globally:
Then add it to your Claude config file (~/.claude.json or ~/.config/claude/config.json):
Restart Claude Code after saving, and you're ready to go.
How it works
The server exposes only two tools with concise descriptions (~1.3K tokens), keeping your context window lean and efficient:
lookup: Gets quick facts from documentation (like API syntax or config keys)
answer: Does deeper research to compare options and make recommendations
Under the hood, both tools are opinionated wrappers that call Perplexity API with coding-specialized system prompts. The lookup tool uses a compact fact‑extraction prompt focused on code/docs facts (see LOOKUP_SYSTEM_PROMPT in src/index.ts). The answer tool uses a technical decision/analysis prompt tailored for migrations and architecture choices (see ANSWER_SYSTEM_PROMPT in src/index.ts). The server also selects task‑appropriate Perplexity models—sonar-pro for lookups (see getLookupModel() in src/index.ts) and sonar-reasoning-pro for deeper research (see getAnswerModel() in src/index.ts).
Example AI agent prompt that will trigger AI agent to use this MCP and give you good results:
Requirements
Node.js v22.14.0 or newer
A Perplexity API key