LinkTwin for AI agents
LinkTwin is a link management platform for creating shortened deep links and tracking their clicks, domains, pixels, and QR codes across 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 LinkTwin.
Create a tracked deep link
Create a new shortened link with tracking for a campaign landing page.
Check a link's click analytics
Pull click analytics for a link to report on campaign performance, read-only.
Approve before deleting a link
Require approval before deleting a link, since existing shares and QR codes would stop resolving.
10 LinkTwin actions, graded by risk.
Every LinkTwin action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
7Look things up. Allowed by default.
- linktwin.get_linkGet Link
- linktwin.list_linksList Links
- linktwin.list_pixelsList Pixels
- linktwin.list_domainsList Domains
- linktwin.get_account_infoGet Account Info
- linktwin.list_collectionsList Collections
- linktwin.get_link_analyticsGet Link Analytics
write
2Create and change things. Allow, or ask the user first.
- linktwin.create_linkCreate Link
- linktwin.update_linkUpdate Link
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- linktwin.delete_linkDelete Link
LinkTwin in three steps.
- 01Your users connect LinkTwinThey add their LinkTwin api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Link” can wait for the user, and “delete Link” can be denied outright.
- 03Any agent can actYour agent calls LinkTwin through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('linktwin', { read: 'allow', write: 'ask', // create_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
How LinkTwin connects.
Users add their LinkTwin 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 LinkTwin 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 LinkTwin from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
LinkTwin and Arc0, answered.
Can I use LinkTwin with Claude, ChatGPT or Cursor?
Yes. Connect LinkTwin 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 LinkTwin actions you allow.
How do users connect LinkTwin?
Users add their LinkTwin 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 LinkTwin actions can my agent take?
10 in total: 7 read, 2 write and 1 destructive, such as “create Link”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in LinkTwin?
Yes. Actions like “delete 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.
Can my own backend call LinkTwin too?
Yes. The same LinkTwin connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug LinkTwin into your agent.
Your users connect LinkTwin once, under your brand. Your agent gets 10 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan