Adrapid for AI agents
Adrapid is a template-based tool for producing digital marketing visuals like banners, images and video ads through an API. Marketing teams use it to automate creative production. 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 Adrapid.
List existing banners
Browse the banner templates already created in the account before generating a new batch of ad creative.
Check account API info
Look up the account's API usage and plan details before running a large export of banner variants.
Look up user account details
Retrieve the current user's account information tied to the API key in use.
3 Adrapid actions, graded by risk.
Every Adrapid 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.
- adrapid.get_api_infoGet API info
- adrapid.list_bannersList Banners
- adrapid.get_system_meGet user and API info
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Adrapid in three steps.
- 01Your users connect AdrapidThey add their Adrapid api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
- 03Any agent can actYour agent calls Adrapid through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('adrapid', { read: 'allow', write: 'ask', destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Adrapid connects.
Users add their Adrapid 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 Adrapid 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 Adrapid from any agent.
Adrapid and Arc0, answered.
Can I use Adrapid with Claude, ChatGPT or Cursor?
Yes. Connect Adrapid 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 Adrapid actions you allow.
How do users connect Adrapid?
Users add their Adrapid 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 Adrapid actions can my agent take?
3 in total: 3 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Adrapid?
Yes. Allow read actions and deny writes in the Adrapid policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Adrapid too?
Yes. The same Adrapid connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Adrapid into your agent.
Your users connect Adrapid once, under your brand. Your agent gets 3 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan