Perplexity AI

by family-it-guy

2 stars
Not rated
GitHub

About

Connects Claude Desktop to Perplexity AI's language models through a lightweight proxy, offering web search capabilities with llama-3.1-sonar-small-128k-online and multi-turn conversations with mixtral-8x7b-instruct.

Details

Author
family-it-guy
Repository
Family-IT-Guy/perplexity-mcp
GitHub stars
2
License
ISC License
Categories
Search, Other, AI, Developer Tools, Design, Community, API, Security, Communication
Tags
#web

- Intelligent Model Selection: Auto-picks the right Perplexity model based on your query
- Research History: Saves all research to ~/Documents/Perplexity Research/
- Multi-Model Synthesis: Combines multiple models for comprehensive research
- Search History: Search past research to avoid duplicate queries
- Built-in Citations: Every response includes sources and references

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Perplexity AI
    Command (node, npx, python, etc.) npx
    Arguments
    • Argument 1 -y
    • Argument 2 @familyitguy/perplexity-mcp
    Environment
    • PERPLEXITY_API_KEY your-api-key-here

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Open ~/Library/Application Support/Claude/claude_desktop_config.json and add:

{
  "mcpServers": {
    "perplexity-research": {
      "command": "npx",
      "args": ["-y", "@familyitguy/perplexity-mcp"],
      "env": {
        "PERPLEXITY_API_KEY": "your-api-key-here"
      }
    }
  }
}

Replace your-api-key-here with your Perplexity API key.

research

Intelligent Perplexity search with auto-logging. Use this to research specific topics.

deep_research

Multi-model synthesis for comprehensive research. Use this for in-depth studies on complex topics.

search_research

Search past research for existing findings. Use this to find previous research on a specific topic.

list_research_threads

List all saved research threads.

read_research_thread

Read a specific past research thread.

list_models

Show available Perplexity models and when to use each.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "perplexity ai": {
            "env": {
                "PERPLEXITY_API_KEY": "your-api-key-here"
            },
            "args": [
                "-y",
                "@familyitguy/perplexity-mcp"
            ],
            "command": "npx"
        }
    }
}

Linux

{
    "env": {
        "PERPLEXITY_API_KEY": "your-api-key-here"
    },
    "args": [
        "-y",
        "@familyitguy/perplexity-mcp"
    ],
    "command": "npx"
}

Macos

{
    "env": {
        "PERPLEXITY_API_KEY": "your-api-key-here"
    },
    "args": [
        "-y",
        "@familyitguy/perplexity-mcp"
    ],
    "command": "npx"
}

Windows

{
    "env": {
        "PERPLEXITY_API_KEY": "your-api-key-here"
    },
    "args": [
        "/c",
        "npx",
        "-y",
        "@familyitguy/perplexity-mcp"
    ],
    "command": "cmd"
}

Adds Perplexity AI as a tool provider for Claude Desktop.

An intelligent Perplexity research MCP server for Claude Desktop with automatic model selection, multi-model synthesis, and persistent research history.

- Intelligent Model Selection: Auto-picks the right Perplexity model based on your query
- Research History: Saves all research to~/Documents/Perplexity Research/
- Multi-Model Synthesis: Combines multiple models for comprehensive research
- Search History: Search past research to avoid duplicate queries
- Built-in Citations: Every response includes sources and references

- Node.js 18+ (download)
- Claude Desktop
- Perplexity API key (get one at
perplexity.ai/settings/api)

Open~/Library/Application Support/Claude/claude_desktop_config.jsonand add:

{ "mcpServers": { "perplexity-research": { "command": "npx", "args": ["-y", "@familyitguy/perplexity-mcp"], "env": { "PERPLEXITY_API_KEY": "your-api-key-here" } } } }

Replaceyour-api-key-herewith your Perplexity API key.

Quit completely (Cmd+Q) and reopen. You're done!

Intelligent Perplexity search with auto-logging.

Use: "Research the current state of AI in healthcare"

Multi-model synthesis for comprehensive research.

Use: "Do a deep research on renewable energy trends"

Search past research for existing findings.

Use: "Search my research for React performance"

Show available Perplexity models and when to use each.

~/Documents/Perplexity Research/ ├── topic-name-2025-01-15.md ├── another-topic-2025-01-16.md └── ...

You can browse your research history in Finder anytime.

Search global news using natural language. Webz.io News Search API returns the most relevant articles and content, with filters for source, country, language, date, sentiment, and category.

A connector for the Perplexity API to enable web search within the MCP ecosystem.

Structural AI Search Readiness MCP. Audit, dry-run fixes, rescore, doctor. No LLM rankings.

Perform web searches with the Brave Search API and analyze research papers using Google's Gemini model.

Provides AI-powered web search and summarization using the Gemini API's grounding feature.

Integrate search grounded Gemini output into your workflow.

Generates responses using the Gemini API and Google Search for up-to-date information.

Performs web searches using the Gemini Web Search Tool via the local gemini-cli.

A server providing Google AI-powered search and documentation tools for developers.

Comprehensive web, news, and social media search and analysis using xAI's Grok API.

Enhances LLM responses with factual, real-time web content using Jina AI's grounding capabilities.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.