U301 for AI agents

U301 is a URL shortener, used by teams that want branded, trackable short links for campaigns and shares. 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 + RESTu301.com
AUDIT LOG · U301POLICY: acme-support
09:41:07 · claude · u_8f2read
u301.list_shorten_domains
List available domains for URL shortening✓ allowed · 212ms
09:41:09 · claude · u_8f2write
u301.shorten_link
Shorten a long URL✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
u301.delete_link
Delete a shortened link✕ blocked · policy: deny
EVERY U301 CALL, ON THE RECORD
01 · USE CASES

What agents do in U301.

01

Shorten a long URL

Create a short link for a long URL using an available domain.

02

List domains available for shortening

Check which domains can be used for a new short link, a read-only lookup.

03

Confirm before deleting a shortened link

Check with the user before deleting a shortened link, since existing shares would break.

02 · ACTIONS

3 U301 actions, graded by risk.

Every U301 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.

  • u301.list_shorten_domains
    List available domains for URL shortening

write

1

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

  • u301.shorten_link
    Shorten a long URL

destructive

1

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

  • u301.delete_link
    Delete a shortened link
03 · HOW IT WORKS

U301 in three steps.

  1. 01Your users connect U301They add their U301 api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “shorten a long URL” can wait for the user, and “delete a shortened link” can be denied outright.
  3. 03Any agent can actYour agent calls U301 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('u301', {
  read: 'allow',
  write: 'ask',        // shorten_link
  destructive: 'deny',  // delete_link
})

# 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 U301 connects.

Users add their U301 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 U301 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 U301 from any agent.

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

U301 and Arc0, answered.

Q01

Can I use U301 with Claude, ChatGPT or Cursor?

Yes. Connect U301 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 U301 actions you allow.

Q02

How do users connect U301?

Users add their U301 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 U301 actions can my agent take?

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

Q04

Can I stop my agent from deleting things in U301?

Yes. Actions like “delete a shortened link” 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 U301 too?

Yes. The same U301 connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug U301 into your agent.

Your users connect U301 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