Get started

Perplexity AI for AI agents

Perplexity AI provides conversational AI models for generating natural-language responses, along with search-grounded answers. Developers and researchers use it to add AI chat and search to their tools. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Connect Perplexity AISee the 9 actions ↓
AI and modelsAPI keyMCP + RESTperplexity.ai
AUDIT LOG · PERPLEXITY AIPOLICY: acme-support
09:41:07 · claude · u_8f2read
perplexity_ai.list_models
List Models✓ allowed · 212ms
09:41:08 · claude · u_8f2read
perplexity_ai.search
Perplexity Search (Raw Results)✓ allowed · 164ms
09:41:09 · claude · u_8f2write
perplexity_ai.create_embeddings
CreateEmbeddings✓ approved · approved by user
EVERY PERPLEXITY AI CALL, ON THE RECORD
01 · USE CASES

What agents do in Perplexity AI.

01

Generate a chat completion

Send a prompt and get a generated response for use in an application or workflow.

02

Run a search-grounded query

Ask a question and get an answer grounded in current search results rather than model memory alone.

03

Check async completion status read-only

Poll a long-running chat completion job to see if it has finished.

02 · ACTIONS

9 Perplexity AI actions, graded by risk.

Every Perplexity AI action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

4

Look things up. Allowed by default.

  • perplexity_ai.list_models
    List Models
  • perplexity_ai.get_async_chat_completion
    Get Async Chat Completion
  • perplexity_ai.list_async_chat_completions
    List Async Chat Completions
  • perplexity_ai.search
    Perplexity Search (Raw Results)

write

5

Create and change things. Allow, or ask the user first.

  • perplexity_ai.create_embeddings
    CreateEmbeddings
  • perplexity_ai.create_chat_completion
    Create Chat Completion
  • perplexity_ai.create_async_chat_completion
    Create Async Chat Completion
  • perplexity_ai.create_contextualized_embeddings
    Create Contextualized Embeddings
  • perplexity_ai.execute_agent
    Execute Agent

destructive

0

Delete, cancel or archive. Ask first, or deny outright.

  • No destructive actions.
03 · HOW IT WORKS

Perplexity AI in three steps.

  1. 01Your users connect Perplexity AIThey add their Perplexity AI api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “createEmbeddings” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Perplexity AI through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('perplexity_ai', {
  read: 'allow',
  write: 'ask',        // create_embeddings
  destructive: 'deny',  
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Perplexity AI connects.

Users add their Perplexity AI api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Perplexity AI connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Perplexity AI from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More ai and models apps.

Affinda119 actionsAgent Mail5 actionsAI/ML API30 actionsAivoov1 actionsAll Images AI7 actionsAltText.ai10 actionsAltTextLab2 actionsAnchor Browser64 actions
ALL AI AND MODELS APPS →
07 · FAQ

Perplexity AI and Arc0, answered.

Q01

Can I use Perplexity AI with Claude, ChatGPT or Cursor?

Yes. Connect Perplexity AI to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Perplexity AI actions you allow.

Q02

How do users connect Perplexity AI?

Users add their Perplexity AI api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Perplexity AI actions can my agent take?

9 in total: 4 read, 5 write and 0 destructive, such as “createEmbeddings”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Perplexity AI?

Yes. Allow read actions and deny writes in the Perplexity AI policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call Perplexity AI too?

Yes. The same Perplexity AI connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Perplexity AI into your agent.

Your users connect Perplexity AI once, under your brand. Your agent gets 9 actions behind your policies, with every call on the record.

Connect Perplexity AIBrowse all apps →

Free to build · MCP + REST · Audit log on every plan