TwitterShots for AI agents
TwitterShots renders public X posts as image screenshots, used by marketers and content teams who want to quote or embed a post as an image rather than a link. 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 TwitterShots.
Generate a screenshot of a post
Turn a public X post into an image for use in a newsletter or slide.
Get a post's content
Pull a tweet's text and metadata as a read-only lookup before rendering it.
Check API usage
Read remaining usage on the account before generating a large batch of screenshots.
5 TwitterShots actions, graded by risk.
Every TwitterShots 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.
- twittershots.get_api_usageGet API Usage
- twittershots.get_tweet_contentGet Tweet Content
- twittershots.get_bulk_tweet_contentGet Bulk Tweet Content
write
2Create and change things. Allow, or ask the user first.
- twittershots.generate_tweet_screenshotGenerate Tweet Screenshot
- twittershots.generate_temporary_screenshot_urlGenerate Temporary Screenshot URL
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
TwitterShots in three steps.
- 01Your users connect TwitterShotsThey add their TwitterShots api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “generate Tweet Screenshot” can wait for the user to approve.
- 03Any agent can actYour agent calls TwitterShots through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('twittershots', { read: 'allow', write: 'ask', // generate_tweet_screenshot destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How TwitterShots connects.
Users add their TwitterShots 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 TwitterShots 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 TwitterShots from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
TwitterShots and Arc0, answered.
Can I use TwitterShots with Claude, ChatGPT or Cursor?
Yes. Connect TwitterShots 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 TwitterShots actions you allow.
How do users connect TwitterShots?
Users add their TwitterShots 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 TwitterShots actions can my agent take?
5 in total: 3 read, 2 write and 0 destructive, such as “generate Tweet Screenshot”. Your policies decide which of them each agent may call.
Can I make my agent read-only in TwitterShots?
Yes. Allow read actions and deny writes in the TwitterShots policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call TwitterShots too?
Yes. The same TwitterShots connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug TwitterShots into your agent.
Your users connect TwitterShots once, under your brand. Your agent gets 5 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan