Download PDFMarkdown Version
ClaudeChatGPTPerplexityGeminiMicrosoft CopilotRaycastMeta AIGrokZ.aiQwenKimi
DeepSeekMistralCursorVS CodeWindsurfJetBrainsClineLovableVercel AI SDKLangChain

Use Perplexity AI with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Access Perplexity's AI search and chat models. get web-grounded answers with citations, search the web and run AI conversations from any AI agent.

Included with plan

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Complete set · 8 capabilities

The complete Perplexity AI capability set.

These are the exact actions your AI can choose when you ask it to work with Perplexity AI.

Capability set01 / 02

01-04

4 capabilities in this set.

Part of 8 available through Perplexity AI.

  1. 01

    Chat with reasoning

    Requires messages array in JSON format. Optionally set max_tokens, temperature and reasoning_effort (low, medium, high). Returns the assistant's response with detailed reasoning chain. Send a message to the Sonar Reasoning model for step-by-step reasoning

  2. 02

    Get usage

    Useful for monitoring API consumption and staying within usage limits. Get API usage statistics

  3. 03

    List models

    Each model returns its ID (e.g. "sonar", "sonar-pro", "sonar-reasoning", "sonar-reasoning-pro"), display name and capabilities. Use this to discover which models are available and their IDs for use with the chat and sonar capabilities. List all available Perplexity models

  4. 04

    Search

    Returns search results with snippets, citations and source URLs. Requires the search query. Optionally set max_results and domain filter to limit results to specific websites. Search the web using Perplexity Search API

Capability set02 / 02

05-08

4 capabilities in this set.

Part of 8 available through Perplexity AI.

  1. 05

    Sonar

    This is the core search-enhanced model. Requires messages array in JSON format. Optionally set max_tokens and temperature. Returns the assistant's response with web citations. Send a message to the Sonar model for web-grounded responses

  2. 06

    Chat

    Requires the model ID (e.g. "sonar", "sonar-pro", "sonar-reasoning") and messages array in JSON format. Each message must have a "role" ("user", "assistant" or "system") and "content" (text). Optionally set max_tokens, temperature (0-1), top_p (0-1), search domain filter, and whether to return images or related questions. Returns the assistant's response with citations. Send a chat message to a Perplexity model

  3. 07

    Chat pro

    Requires messages array in JSON format. Optionally set max_tokens and temperature. Returns the assistant's response with citations. Send a chat message to the Sonar Pro model for enhanced responses

  4. 08

    Chat with reasoning pro

    Requires messages array in JSON format. Optionally set max_tokens, temperature and reasoning_effort (low, medium, high). Returns the assistant's response with detailed reasoning chain and citations. Send a message to the Sonar Reasoning Pro model for deep reasoning

Observed, not estimated

865ms average. Fast in production.

Perplexity AI is checked daily against the live service.

Daily averagePeak 1080ms
Aug 20Today
Fastest day
737ms
Slowest day
1080ms
14-day trend
Slowing+14%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 8 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Perplexity AI, so you can see the experience inside your AI.

It does not authenticate your account with Perplexity AI. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Perplexity AI Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_UbSKRkwZQEYfv4pzyvcNwmqlKwk5UEhIITyylXnJ/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Perplexity AI capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "perplexity-ai-alternative-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_UbSKRkwZQEYfv4pzyvcNwmqlKwk5UEhIITyylXnJ/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

FAQ

Questions Perplexity AI owners ask.

  • 01

    How do I get a Perplexity API key?

    Log in to the Perplexity AI Settings, go to API Key Management and click Create API Key. Copy the key immediately. it starts with pplx- and won't be shown again.

  • 02

    What models are available?

    Use the list_models capability to see all available Perplexity models. Key models include sonar (web-grounded chat), sonar-pro (enhanced reasoning), sonar-reasoning and sonar-reasoning-pro. Each model provides real-time web search with citations.

  • 03

    Can I filter search results to specific domains?

    Yes! Use the chat or search capabilities with the search_domains parameter to limit results to specific websites (e.g. ["wikipedia.org","github.com"]). This is useful for research focused on trusted sources.

  • 04

    Do responses include citations?

    Yes! All Sonar models return responses with inline citations and a list of source URLs. The citations are embedded in the response text as numbered references [1], [2], etc., and the full source URLs are provided in the response metadata.

Explore

More in AI Frontier

Suggestions