Get started

PromptHub for AI agents

PromptHub manages, versions, and executes prompts and prompt projects for teams building with LLMs. AI and product teams use it to keep prompt changes tracked and testable. 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.

Connect PromptHubSee the 4 actions ↓
AI and modelsAPI keyMCP + RESTprompthub.us
AUDIT LOG · PROMPTHUBPOLICY: acme-support
09:41:07 · claude · u_8f2read
prompthub.list_projects
List Projects✓ allowed · 212ms
09:41:08 · claude · u_8f2read
prompthub.get_current_team
Get Current Team✓ allowed · 164ms
09:41:09 · claude · u_8f2write
prompthub.run_project
Run Project✓ approved · approved by user
EVERY PROMPTHUB CALL, ON THE RECORD
01 · USE CASES

What agents do in PromptHub.

01

Run a prompt project

Execute a saved prompt project against input data and return the model's response.

02

Check a project's current version read-only

Look up a project's head version before deciding whether to run or update it.

03

Check team projects read-only

List projects available to the current team before starting a new run.

02 · ACTIONS

4 PromptHub actions, graded by risk.

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

read

3

Look things up. Allowed by default.

  • prompthub.list_projects
    List Projects
  • prompthub.get_current_team
    Get Current Team
  • prompthub.get_project_head
    Get Project Head

write

1

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

  • prompthub.run_project
    Run Project

destructive

0

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

  • No destructive actions.
03 · HOW IT WORKS

PromptHub in three steps.

  1. 01Your users connect PromptHubThey add their PromptHub api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “run Project” can wait for the user to approve.
  3. 03Any agent can actYour agent calls PromptHub 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('prompthub', {
  read: 'allow',
  write: 'ask',        // run_project
  destructive: 'deny',  
})

# 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 PromptHub connects.

Users add their PromptHub 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 PromptHub 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 PromptHub from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More ai and models apps.

Perplexity AI9 actionsAffinda119 actionsAgent Mail5 actionsAI/ML API30 actionsAivoov1 actionsAll Images AI7 actionsAltText.ai10 actionsAltTextLab2 actions
ALL AI AND MODELS APPS →
07 · FAQ

PromptHub and Arc0, answered.

Q01

Can I use PromptHub with Claude, ChatGPT or Cursor?

Yes. Connect PromptHub 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 PromptHub actions you allow.

Q02

How do users connect PromptHub?

Users add their PromptHub 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 PromptHub actions can my agent take?

4 in total: 3 read, 1 write and 0 destructive, such as “run Project”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in PromptHub?

Yes. Allow read actions and deny writes in the PromptHub policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call PromptHub too?

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

Get started

Plug PromptHub into your agent.

Your users connect PromptHub once, under your brand. Your agent gets 4 actions behind your policies, with every call on the record.

Connect PromptHubBrowse all apps →

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