How do I use Perplexity with Claude or Cursor?

Once you subscribe to this MCP on Vinkius and add your API key, you can connect it to any MCP-compatible client like Claude, Cursor, or Windsurf with one click.

Does this MCP provide citations?

Yes. The chat and search capabilities return responses that include specific citations and source URLs so you can verify the information.

Can I limit my search to certain websites?

Yes. The search capability includes a domain filter that allows you to restrict results to specific websites.

What is the difference between the Sonar models?

The models vary by capability. Sonar is the standard search-enhanced model, Sonar Pro offers enhanced responses, and the Reasoning models provide a detailed step-by-step reasoning chain.

How can I check how much of my API quota I have left?

You can use the get_usage capability to pull your current API consumption statistics directly through your AI client.

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.

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.

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.

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.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Perplexity AI (Alternative) to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Get real-time answers with verified citations in your workspace.

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.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 8 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-04

4 capabilities in this set.

Part of 8 available through Perplexity AI.

01
Chat
Sends a conversation to a Perplexity model of your choice. It returns the response along with specific web citations.
02
Chat pro
Uses the Sonar Pro model to generate more advanced, high-quality responses with included citations.
03
Chat with reasoning
Triggers the Sonar Reasoning model to provide a detailed, step-by-step reasoning chain for complex queries.
04
Chat with reasoning pro
Combines deep reasoning with the Pro model to deliver thorough, multi-step logical breakdowns and citations.

Capability set02 / 02

05-08

4 capabilities in this set.

Part of 8 available through Perplexity AI.

05
Get usage
Checks your current API consumption so you can track your usage against your limits.
06
List models
Retrieves a list of all available Perplexity models and their specific capabilities.
07
Search
Performs a direct web search to return snippets, source URLs, and citations for a specific query.
08
Sonar
Uses the core Sonar model to provide web-grounded answers with direct citations.

Real work

What teams actually run

Fact-Checking

Verify a specific claim by having your agent search for recent news and primary sources.

Technical Research

Use reasoning models to understand new software documentation or scientific breakthroughs.

Market Monitoring

Get real-time updates on asset prices or industry trends using the search capability.

Competitive Intelligence

Filter searches to specific competitor domains to gather structured information.

Automate a task

Put Perplexity AI to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Perplexity AI works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Perplexity AI to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

906ms average. Fast in production.

Perplexity AI is checked daily against the live service.

Daily averagePeak 1336ms

Oct 3Today

Fastest day: 672ms
Slowest day: 1336ms
14-day trend: Improving-34%

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.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
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

Guided setup for Claude? Set up Perplexity AI in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Perplexity AI owners hand off.

This MCP is built for anyone who needs an AI agent that can perform accurate, real-time research without leaving their primary workspace.

01
Researchers
They use the capability to fact-check claims and conduct literature reviews using cited web data.
02
Developers
They integrate web search and chat capabilities into their own applications via the API.
03
Analysts
They use domain filtering to pull structured search results from specific industry websites.

FAQ

Questions Perplexity AI owners ask.

01
How do I use Perplexity with Claude or Cursor?
Once you subscribe to this MCP on Vinkius and add your API key, you can connect it to any MCP-compatible client like Claude, Cursor, or Windsurf with one click.
02
Does this MCP provide citations?
Yes. The chat and search capabilities return responses that include specific citations and source URLs so you can verify the information.
03
Can I limit my search to certain websites?
Yes. The search capability includes a domain filter that allows you to restrict results to specific websites.
04
What is the difference between the Sonar models?
The models vary by capability. Sonar is the standard search-enhanced model, Sonar Pro offers enhanced responses, and the Reasoning models provide a detailed step-by-step reasoning chain.
05
How can I check how much of my API quota I have left?
You can use the get_usage capability to pull your current API consumption statistics directly through your AI client.
06
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.
07
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.
08
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.
09
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

Connect Perplexity AI to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Chat

Chat pro

Chat with reasoning

Chat with reasoning pro

05-08

Get usage

List models

Search

Sonar

What teams actually run

Fact-Checking

Technical Research

Market Monitoring

Competitive Intelligence

Building your own app? The connector is yours to use.

Perplexity AI Connector

Claude Desktop

Researchers

Developers

Analysts

How do I use Perplexity with Claude or Cursor?

Does this MCP provide citations?

Can I limit my search to certain websites?

What is the difference between the Sonar models?

How can I check how much of my API quota I have left?

How do I get a Perplexity API key?

What models are available?

Can I filter search results to specific domains?

Do responses include citations?

Bing Search AI Connector

Bing Search AI Connector

Linkup (AI Search & RAG) AI Connector

Data Pipeline Prover AI Connector

Suggestions

QuestDB (Time-Series) AI Connector

Scale SERP AI Connector

PubNub (Real-time Messaging) AI Connector

Goldsky (Web3 Data Indexing & Subgraphs) AI Connector