Promptmate.io for AI agents

Promptmate.io lets teams build AI-powered applications that combine tools like ChatGPT, Gemini, and Stability AI into multi-step workflows. Teams use it to automate bulk AI processing tasks. 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.

AI and modelsAPI keyMCP + RESTpromptmate.io
AUDIT LOG · PROMPTMATE.IOPOLICY: acme-support
09:41:07 · claude · u_8f2read
promptmate_io.list_apps
List PromptMate Apps✓ allowed · 212ms
09:41:08 · claude · u_8f2read
promptmate_io.get_app_job
Get App Job Status✓ allowed · 164ms
09:41:09 · claude · u_8f2write
promptmate_io.create_webhook
Create webhook✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
promptmate_io.delete_webhook
Delete Webhook✕ blocked · policy: deny
EVERY PROMPTMATE.IO CALL, ON THE RECORD
01 · USE CASES

What agents do in Promptmate.io.

01

Run a saved template

Use a saved prompt template against new input to generate an AI-powered result.

02

Check an app job's status read-only

Poll a running app job to see if a bulk processing task has finished.

03

Delete a webhook with approval

Remove a webhook only after confirming no workflow still depends on it.

02 · ACTIONS

11 Promptmate.io actions, graded by risk.

Every Promptmate.io action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

8

Look things up. Allowed by default.

  • promptmate_io.list_apps
    List PromptMate Apps
  • promptmate_io.get_app_job
    Get App Job Status
  • promptmate_io.get_user_info
    Get User Info
  • promptmate_io.list_projects
    List Projects
  • promptmate_io.list_webhooks
    List Webhooks
  • promptmate_io.list_countries
    List Countries
  • promptmate_io.list_languages
    List Available Languages
  • promptmate_io.list_templates
    List Templates

write

2

Create and change things. Allow, or ask the user first.

  • promptmate_io.create_webhook
    Create webhook
  • promptmate_io.use_template
    Use Template

destructive

1

Delete, cancel or archive. Ask first, or deny outright.

  • promptmate_io.delete_webhook
    Delete Webhook
03 · HOW IT WORKS

Promptmate.io in three steps.

  1. 01Your users connect Promptmate.ioThey add their Promptmate.io api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create webhook” can wait for the user, and “delete Webhook” can be denied outright.
  3. 03Any agent can actYour agent calls Promptmate.io through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('promptmate_io', {
  read: 'allow',
  write: 'ask',        // create_webhook
  destructive: 'deny',  // delete_webhook
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Promptmate.io connects.

Users add their Promptmate.io 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 Promptmate.io 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
05 · WORKS WITH

Use Promptmate.io from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Promptmate.io and Arc0, answered.

Q01

Can I use Promptmate.io with Claude, ChatGPT or Cursor?

Yes. Connect Promptmate.io 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 Promptmate.io actions you allow.

Q02

How do users connect Promptmate.io?

Users add their Promptmate.io 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.

Q03

Which Promptmate.io actions can my agent take?

11 in total: 8 read, 2 write and 1 destructive, such as “create webhook”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Promptmate.io?

Yes. Actions like “delete Webhook” 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.

Q05

Can my own backend call Promptmate.io too?

Yes. The same Promptmate.io connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Promptmate.io into your agent.

Your users connect Promptmate.io once, under your brand. Your agent gets 11 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan