Abyssale for AI agents
Abyssale is a creative automation platform for generating images, videos and HTML5 banners from templates at scale. Marketing teams use it to produce ad variants programmatically. 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 Abyssale.
List available designs
Browse the design templates already set up in a project before generating new creative assets.
Create a new project
Set up a new project to hold a set of banner or video templates for a campaign.
Check available fonts
Pull the list of fonts loaded into the account before applying one to a new design template.
4 Abyssale actions, graded by risk.
Every Abyssale action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
2Look things up. Allowed by default.
- abyssale.get_fontsGet Fonts
- abyssale.get_designsGet Designs
write
2Create and change things. Allow, or ask the user first.
- abyssale.create_projectCreate Abyssale Project
- abyssale.authentication_testTest Abyssale Authentication
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Abyssale in three steps.
- 01Your users connect AbyssaleThey add their Abyssale api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “create Abyssale Project” can wait for the user to approve.
- 03Any agent can actYour agent calls Abyssale through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('abyssale', { read: 'allow', write: 'ask', // create_project destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Abyssale connects.
Users add their Abyssale 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 Abyssale 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 Abyssale from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Abyssale and Arc0, answered.
Can I use Abyssale with Claude, ChatGPT or Cursor?
Yes. Connect Abyssale 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 Abyssale actions you allow.
How do users connect Abyssale?
Users add their Abyssale 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 Abyssale actions can my agent take?
4 in total: 2 read, 2 write and 0 destructive, such as “create Abyssale Project”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Abyssale?
Yes. Allow read actions and deny writes in the Abyssale policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Abyssale too?
Yes. The same Abyssale connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Abyssale into your agent.
Your users connect Abyssale 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