AltTextLab for AI agents
AltTextLab generates accessible, search-friendly alt text for images from an API. Content teams and developers use it to fill in missing image descriptions across websites without writing each one by hand. 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 AltTextLab.
Generate alt text for an image
Produce SEO-aware, accessible alt text for a product photo or blog image automatically.
Check remaining credits before a batch job
Look up the account's credit balance before generating alt text for a large batch of images.
Review generated text before publishing
Have a person confirm the generated alt text is accurate before it is applied to live pages.
2 AltTextLab actions, graded by risk.
Every AltTextLab action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
1Look things up. Allowed by default.
- alttextlab.get_account_creditsGet Account Credits
write
1Create and change things. Allow, or ask the user first.
- alttextlab.generate_alt_textGenerate Alt Text
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
AltTextLab in three steps.
- 01Your users connect AltTextLabThey add their AltTextLab api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “generate Alt Text” can wait for the user to approve.
- 03Any agent can actYour agent calls AltTextLab through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('alttextlab', { read: 'allow', write: 'ask', // generate_alt_text destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How AltTextLab connects.
Users add their AltTextLab 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 AltTextLab 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 AltTextLab from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
AltTextLab and Arc0, answered.
Can I use AltTextLab with Claude, ChatGPT or Cursor?
Yes. Connect AltTextLab 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 AltTextLab actions you allow.
How do users connect AltTextLab?
Users add their AltTextLab 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 AltTextLab actions can my agent take?
2 in total: 1 read, 1 write and 0 destructive, such as “generate Alt Text”. Your policies decide which of them each agent may call.
Can I make my agent read-only in AltTextLab?
Yes. Allow read actions and deny writes in the AltTextLab policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call AltTextLab too?
Yes. The same AltTextLab connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug AltTextLab into your agent.
Your users connect AltTextLab once, under your brand. Your agent gets 2 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan