AltText.ai for AI agents
AltText.ai automatically generates alt text for images to improve accessibility and search visibility. E-commerce teams and publishers use it to describe product photos and blog images at scale. 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 AltText.ai.
Generate alt text for a batch
Bulk-create alt text across a set of product photos in a single pass.
Scrape a page for missing alt text
Scan a webpage for images and generate alt text for any that lack it.
Confirm before removing an image record
Deleting an image by its asset ID is destructive and should be approved before it happens.
10 AltText.ai actions, graded by risk.
Every AltText.ai action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
5Look things up. Allowed by default.
- alttext_ai.get_imagesGet Images
- alttext_ai.get_accountGet Account
- alttext_ai.search_imagesSearch Images
- alttext_ai.get_image_by_asset_idGet Image by Asset ID
- alttext_ai.scrape_pageScrape Page for Images
write
4Create and change things. Allow, or ask the user first.
- alttext_ai.create_imageCreate Image
- alttext_ai.update_accountUpdate Account
- alttext_ai.create_bulk_imagesBulk Create Images
- alttext_ai.update_image_by_asset_idUpdate Image by Asset ID
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- alttext_ai.delete_image_by_asset_idDelete Image by Asset ID
AltText.ai in three steps.
- 01Your users connect AltText.aiThey add their AltText.ai api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Image” can wait for the user, and “delete Image by Asset ID” can be denied outright.
- 03Any agent can actYour agent calls AltText.ai through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('alttext_ai', { read: 'allow', write: 'ask', // create_image destructive: 'deny', // delete_image_by_asset_id }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How AltText.ai connects.
Users add their AltText.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 AltText.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
Use AltText.ai from any agent.
AltText.ai and Arc0, answered.
Can I use AltText.ai with Claude, ChatGPT or Cursor?
Yes. Connect AltText.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 AltText.ai actions you allow.
How do users connect AltText.ai?
Users add their AltText.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.
Which AltText.ai actions can my agent take?
10 in total: 5 read, 4 write and 1 destructive, such as “create Image”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in AltText.ai?
Yes. Actions like “delete Image by Asset ID” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call AltText.ai too?
Yes. The same AltText.ai connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug AltText.ai into your agent.
Your users connect AltText.ai once, under your brand. Your agent gets 10 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan