Perplexity Ask MCP Server

Name: Perplexity Ask MCP Server
Author: ppl-ai

@ppl-ai

Repository Homepage

About Perplexity Ask MCP Server

The official MCP server implementation for the Perplexity API Platform

#mathgpt #math-solver #math-assistant

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "perplexity-ask": {
      "command": "npx",
      "args": [
        "-y",
        "@chatmcp/server-perplexity-ask"
      ],
      "env": {
        "PERPLEXITY_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Perplexity Ask MCP Server?

It is the official MCP server implementation for the Perplexity API Platform, providing AI assistants with real-time web search, reasoning, and research capabilities through Sonar models and the Search API. It is designed for developers integrating Perplexity into MCP-compatible clients such as Cursor, Claude Desktop, VS Code, and others.

How to use Perplexity Ask MCP Server?

Install the npm package @perplexity-ai/mcp-server and run it via npx -y in stdio mode, or deploy as an HTTP server using Docker or Node.js. Set the PERPLEXITY_API_KEY environment variable to your API key from the Perplexity API Portal. Configure clients by adding a mcpServers entry in their respective config files (e.g., ~/.cursor/mcp.json for Cursor). Optional environment variables include PERPLEXITY_TIMEOUT_MS, PERPLEXITY_BASE_URL, PERPLEXITY_LOG_LEVEL, and PERPLEXITY_PROXY for proxy support.

Key features of Perplexity Ask MCP Server

perplexity_search: Direct web search via the Search API with ranked results and metadata.
perplexity_ask: Conversational AI with real-time web search using the sonar-pro model.
perplexity_research: Deep, comprehensive research using the sonar-deep-research model.
perplexity_reason: Advanced reasoning and problem-solving with the sonar-reasoning-pro model.
Optional strip_thinking parameter for perplexity_reason and perplexity_research to remove thinking tags.
Support for proxy configuration via PERPLEXITY_PROXY or standard HTTPS_PROXY/HTTP_PROXY environment variables.
HTTP deployment mode with configurable port, CORS origins, and allowed hosts.

Use cases of Perplexity Ask MCP Server

Performing quick web searches within an AI assistant to retrieve current information.
Answering everyday questions with conversational AI that includes real-time search context.
Generating thorough research reports and deep analysis on complex topics.
Solving intricate analytical tasks requiring advanced reasoning and multi-step problem-solving.

FAQ from Perplexity Ask MCP Server

Why am I getting an API key error?

Ensure the PERPLEXITY_API_KEY environment variable is set to a valid API key from the Perplexity API Portal.

What should I do if a tool

Comments

More AI & Agents MCP servers

Just Prompt - A lightweight MCP server for LLM providers

disler

just-prompt is an MCP server that provides a unified interface to top LLM providers (OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama)

733

1MCP - One MCP Server for All

1mcp-app

A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.

468

Solon Ai

opensolon

Java AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.

416

Model Context Protocol Server for Home Assistant

tevonsb

A MCP server for Home Assistant

574

Sequential Thinking Multi-Agent System (MAS)

FradSer

An advanced sequential thinking process using a Multi-Agent System (MAS) built with the Agno framework and served via MCP.

306