Use Exa with AI apps and agents through Vercel Connect. Follow a complete setup guide for secure runtime access.
$ npx skills add vercel/vercel-plugin --skill vercel-connect$ vercel connect create exa --name acme-exaimport { getToken } from '@vercel/connect';
const userId = 'user_123';
const token = await getToken('exa/acme-exa', { subject: { type: 'user', id: userId },});Web search and content retrieval for AI agents.
Read the Exa developer docs(opens in new tab)Request Exa credentials only when your application or agent needs them instead of copying secrets into application code.
Support both user-authorized and app-scoped Exa access from the same connection layer.
Manage Exa credentials in one place and retrieve them through a consistent runtime API.
Bind connections to the projects and environments that need them while Vercel OIDC authenticates each runtime request.
Follow a complete setup for the Connect SDK or a supported agent framework.
Add Exa to an existing Vercel application with the Connect SDK.
npm install @vercel/connectRun these commands from the project that will use the connection.
vercel linkvercel connect create exa --name acme-exavercel env pullimport { getToken } from '@vercel/connect';
const userId = 'user_123';
const token = await getToken('exa/acme-exa', { subject: { type: 'user', id: userId },});