L2s for AI agents
L2S is a URL shortener built for teams, offering branded short links, click analytics, and QR codes for marketers running multi-channel campaigns. 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 L2s.
Shorten a campaign link
Create a short link for a new campaign URL so it can be tracked and shared.
Check a link's click details
Look up click stats for an existing shortened URL to report on campaign reach.
List all shortened links
Pull the full list of a workspace's shortened URLs for an audit, read-only.
4 L2s actions, graded by risk.
Every L2s action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
1Look things up. Allowed by default.
- l2s.get_url_detailsGet URL Details
write
3Create and change things. Allow, or ask the user first.
- l2s.l2_s_list_urlsList Shortened URLs
- l2s.l2_s_shorten_urlShorten URL with L2S
- l2s.l2_s_get_user_settingsGet User Settings
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
L2s in three steps.
- 01Your users connect L2sThey add their L2s api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “list Shortened URLs” can wait for the user to approve.
- 03Any agent can actYour agent calls L2s through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('l2s', { read: 'allow', write: 'ask', // l2_s_list_urls destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How L2s connects.
Users add their L2s 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 L2s 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 L2s from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
L2s and Arc0, answered.
Can I use L2s with Claude, ChatGPT or Cursor?
Yes. Connect L2s 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 L2s actions you allow.
How do users connect L2s?
Users add their L2s 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 L2s actions can my agent take?
4 in total: 1 read, 3 write and 0 destructive, such as “list Shortened URLs”. Your policies decide which of them each agent may call.
Can I make my agent read-only in L2s?
Yes. Allow read actions and deny writes in the L2s policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call L2s too?
Yes. The same L2s connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug L2s into your agent.
Your users connect L2s once, under your brand. Your agent gets 4 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan