Cutt.ly for AI agents

Cutt.ly shortens URLs and tracks their performance, giving marketers a way to share cleaner links and see how many people click them. 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.

MarketingAPI keyMCP + RESTcutt.ly
AUDIT LOG · CUTT.LYPOLICY: acme-support
09:41:07 · claude · u_8f2read
cutt_ly.view_last_shortened_urls
View Last Shortened URLs✓ allowed · 212ms
09:41:09 · claude · u_8f2write
cutt_ly.shorten_url
Shorten URL✓ approved · approved by user
EVERY CUTT.LY CALL, ON THE RECORD
01 · USE CASES

What agents do in Cutt.ly.

01

Shorten a URL

Shorten a long URL into a branded short link ready to share in a campaign.

02

Check recently shortened links

View recently shortened URLs before deciding whether to reuse or retire one.

03

Track a link's clicks

Check a shortened link's click count to gauge how a campaign is performing.

02 · ACTIONS

2 Cutt.ly actions, graded by risk.

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

read

1

Look things up. Allowed by default.

  • cutt_ly.view_last_shortened_urls
    View Last Shortened URLs

write

1

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

  • cutt_ly.shorten_url
    Shorten URL

destructive

0

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

  • No destructive actions.
03 · HOW IT WORKS

Cutt.ly in three steps.

  1. 01Your users connect Cutt.lyThey add their Cutt.ly api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “shorten URL” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Cutt.ly 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('cutt_ly', {
  read: 'allow',
  write: 'ask',        // shorten_url
  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 Cutt.ly connects.

Users add their Cutt.ly 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 Cutt.ly 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 Cutt.ly from any agent.

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

Cutt.ly and Arc0, answered.

Q01

Can I use Cutt.ly with Claude, ChatGPT or Cursor?

Yes. Connect Cutt.ly 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 Cutt.ly actions you allow.

Q02

How do users connect Cutt.ly?

Users add their Cutt.ly 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 Cutt.ly actions can my agent take?

2 in total: 1 read, 1 write and 0 destructive, such as “shorten URL”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Cutt.ly?

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

Q05

Can my own backend call Cutt.ly too?

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

Get started

Plug Cutt.ly into your agent.

Your users connect Cutt.ly once, under your brand. Your agent gets 2 actions behind your policies, with every call on the record.

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