How to integrate Perplexity AI using MCP

AI with real-time web search. This guide creates an MCP server from Arthur's Perplexity AI template — tools preconfigured against https://api.perplexity.ai — and finishes by sharing the server's MCP swagger documentation.

Steps

1. Open the Secrets vault and create a secret named PERPLEXITY_API_KEY holding your access token. Generate an API key in your Perplexity account settings at perplexity.ai/settings/api.

   

   

   

2. Go to the REST API Templates gallery and search for Perplexity AI.

   

   

3. Click Use template on the Perplexity AI card to open the server-creation dialog.

   

   

4. Review the server name and select PERPLEXITY_API_KEY in the credential field — the dialog only accepts vault secrets, and it lists every tool that will be created.

   

   

   

5. Click Create server. Arthur creates the server, applies the authentication, and generates all the tools.

   

   

   

   

   

6. Open the server's Tools tab to review the generated tools.

   

7. Open the server's Connect section and click Share the MCP swagger documentation — Arthur generates the public documentation link and QR code for this server.

   

   

   

Confirm it worked

The server appears with 1 preconfigured tool(s): search_and_answer. The Connect section offers the MCP swagger documentation — a shareable page with setup instructions for any AI client.

Good to know

• Query Perplexity AI models that combine LLM reasoning with real-time web search. Get cited, up-to-date answers on any topic.
• This integration requires a credential (bearer). Get one at https://www.perplexity.ai/settings/api.
• Official API documentation: https://docs.perplexity.ai/reference/post_chat_completions
• Editing a tool later never changes the template — templates are starting points, and the server is fully yours after creation.

Related

• REST API Template Gallery
• How to Store and Reference a Secret
• How to Create a Server from a Template