Get started

Openperplex for AI agents

Openperplex provides web search and content analysis built for AI applications, returning structured answers and page content. Developers use it to give agents up-to-date web knowledge. 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 OpenperplexSee the 8 actions ↓
AI and modelsAPI keyMCP + RESTopenperplex.com
AUDIT LOG · OPENPERPLEXPOLICY: acme-support
09:41:07 · claude · u_8f2read
openperplex.search
Search Documents✓ allowed · 212ms
09:41:08 · claude · u_8f2read
openperplex.search_stream
Search Stream✓ allowed · 164ms
09:41:09 · claude · u_8f2write
openperplex.custom_search
Custom Search✓ approved · approved by user
EVERY OPENPERPLEX CALL, ON THE RECORD
01 · USE CASES

What agents do in Openperplex.

01

Run a search query for an answer

Ask a question and get a synthesized answer sourced from current web search results.

02

Get a page as clean markdown

Fetch a webpage's content converted to markdown for easier summarization.

03

Capture a website screenshot

Grab a screenshot of a page to accompany a research summary or citation.

02 · ACTIONS

8 Openperplex actions, graded by risk.

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

read

6

Look things up. Allowed by default.

  • openperplex.search_stream
    Search Stream
  • openperplex.query_from_url
    Query from URL
  • openperplex.get_website_text
    Get Website Text
  • openperplex.get_website_markdown
    Get Website Markdown
  • openperplex.get_website_screenshot
    Get Website Screenshot
  • openperplex.search
    Search Documents

write

2

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

  • openperplex.custom_search
    Custom Search
  • openperplex.custom_search_stream
    Custom Search Stream

destructive

0

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

  • No destructive actions.
03 · HOW IT WORKS

Openperplex in three steps.

  1. 01Your users connect OpenperplexThey add their Openperplex api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “custom Search” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Openperplex 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('openperplex', {
  read: 'allow',
  write: 'ask',        // custom_search
  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 Openperplex connects.

Users add their Openperplex 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 Openperplex 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 Openperplex 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.

Perplexity AI9 actionsAffinda119 actionsAgent Mail5 actionsAI/ML API30 actionsAivoov1 actionsAll Images AI7 actionsAltText.ai10 actionsAltTextLab2 actions
ALL AI AND MODELS APPS →
07 · FAQ

Openperplex and Arc0, answered.

Q01

Can I use Openperplex with Claude, ChatGPT or Cursor?

Yes. Connect Openperplex 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 Openperplex actions you allow.

Q02

How do users connect Openperplex?

Users add their Openperplex 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 Openperplex actions can my agent take?

8 in total: 6 read, 2 write and 0 destructive, such as “custom Search”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Openperplex?

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

Q05

Can my own backend call Openperplex too?

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

Get started

Plug Openperplex into your agent.

Your users connect Openperplex once, under your brand. Your agent gets 8 actions behind your policies, with every call on the record.

Connect OpenperplexBrowse all apps →

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