AI Agent
Use AI Agent with AI apps and agents through Vercel Connect. Follow a complete setup guide for secure runtime access.
Install the skill
$ npx skills add vercel/vercel-plugin --skill vercel-connectConnect to
Use its data in agents and apps
import { getToken } from '@vercel/connect';const userId = 'user_123';const token = await getToken('ai-agent/acme-ai-agent', {subject: { type: 'user', id: userId },});
Use AI Agent in apps and agents
Manage tickets, run agents and workflows, query tables, and search knowledge.
Read the AI Agent developer docs(opens in new tab)Why use Vercel Connect with AI Agent?
Credentials on demand
Request AI Agent credentials only when your application or agent needs them instead of copying secrets into application code.
Access for the right subject
Request user-authorized AI Agent access so actions follow the identity and permissions of the person using your application.
Centralized credential management
Manage AI Agent credentials in one place and retrieve them through a consistent runtime API.
Vercel-native controls
Bind connections to the projects and environments that need them while Vercel OIDC authenticates each runtime request.
Use AI Agent with your stack
Follow a complete setup for the Connect SDK or a supported agent framework.
Add AI Agent to an existing Vercel application with the Connect SDK.
Install the Connect SDK
npm install @vercel/connectCreate the AI Agent connector
Run these commands from the project that will use the connection.
vercel linkvercel connect create ai-agent --name acme-ai-agentvercel env pullRequest AI Agent credentials
app/api/route.tsimport { getToken } from '@vercel/connect';const userId = 'user_123';const token = await getToken('ai-agent/acme-ai-agent', {subject: { type: 'user', id: userId },});
