Y gy for AI agents
y.gy is a URL shortener and QR code generator, used by teams that want short, memorable links with basic tagging and tracking. 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 Y gy.
Create a short link
Generate a short, custom link for a long URL.
Get all links and their stats
Pull the account's links and click counts as a read-only report.
Confirm before deleting a link
Check with the user before deleting a short link, since existing shares of it would break.
8 Y gy actions, graded by risk.
Every Y gy action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
3Look things up. Allowed by default.
- y_gy.get_linkGet Link Details
- y_gy.get_all_tagsGet all tags
- y_gy.get_all_linksGet all links
write
3Create and change things. Allow, or ask the user first.
- y_gy.create_tagCreate Tag
- y_gy.create_linkCreate Y.gy Link
- y_gy.register_userRegister User
destructive
2Delete, cancel or archive. Ask first, or deny outright.
- y_gy.delete_tagDelete a tag by ID
- y_gy.delete_short_linkDelete Y.GY Short Link
Y gy in three steps.
- 01Your users connect Y gyThey add their Y gy api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Tag” can wait for the user, and “delete a tag by ID” can be denied outright.
- 03Any agent can actYour agent calls Y gy through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('y_gy', { read: 'allow', write: 'ask', // create_tag destructive: 'deny', // delete_tag }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Y gy connects.
Users add their Y gy 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 Y gy 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 Y gy from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Y gy and Arc0, answered.
Can I use Y gy with Claude, ChatGPT or Cursor?
Yes. Connect Y gy 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 Y gy actions you allow.
How do users connect Y gy?
Users add their Y gy 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 Y gy actions can my agent take?
8 in total: 3 read, 3 write and 2 destructive, such as “create Tag”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Y gy?
Yes. Actions like “delete a tag by ID” 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 Y gy too?
Yes. The same Y gy connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Y gy into your agent.
Your users connect Y gy once, under your brand. Your agent gets 8 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan