OpenGraph.io for AI agents
OpenGraph.io retrieves Open Graph metadata and preview content from any website, even ones without proper tags defined. Developers use it to generate link previews and page summaries. 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.
What agents do in OpenGraph.io.
Extract metadata for a link preview
Pull a page's title, image, and description to build a rich link preview.
Capture a page screenshot
Generate a screenshot of a URL to include alongside its extracted metadata.
Scrape a page for its HTML
Retrieve the raw HTML of a page for further parsing or archiving.
4 OpenGraph.io actions, graded by risk.
Every OpenGraph.io action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
3Look things up. Allowed by default.
- opengraph_io.scrape_urlScrape URL for HTML
- opengraph_io.scrape_siteScrape Site
- opengraph_io.extract_siteExtract Site Metadata
write
1Create and change things. Allow, or ask the user first.
- opengraph_io.capture_screenshotCapture Screenshot
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
OpenGraph.io in three steps.
- 01Your users connect OpenGraph.ioThey add their OpenGraph.io api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “capture Screenshot” can wait for the user to approve.
- 03Any agent can actYour agent calls OpenGraph.io through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('opengraph_io', { read: 'allow', write: 'ask', // capture_screenshot destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How OpenGraph.io connects.
Users add their OpenGraph.io 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 OpenGraph.io 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
Use OpenGraph.io from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraphMore web data and scraping apps.
OpenGraph.io and Arc0, answered.
Can I use OpenGraph.io with Claude, ChatGPT or Cursor?
Yes. Connect OpenGraph.io 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 OpenGraph.io actions you allow.
How do users connect OpenGraph.io?
Users add their OpenGraph.io 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.
Which OpenGraph.io actions can my agent take?
4 in total: 3 read, 1 write and 0 destructive, such as “capture Screenshot”. Your policies decide which of them each agent may call.
Can I make my agent read-only in OpenGraph.io?
Yes. Allow read actions and deny writes in the OpenGraph.io policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call OpenGraph.io too?
Yes. The same OpenGraph.io connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug OpenGraph.io into your agent.
Your users connect OpenGraph.io once, under your brand. Your agent gets 4 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan