Vercel Connect is now generally available
Vercel Connect is now generally available on all plans, enabling secure runtime authentication with short-lived, scoped tokens instead of storing long-lived provider secrets. It includes 100+ preset connectors, per-environment attachment, audit logs, and supports AI SDK, MCP servers, and webhook triggers without stored secrets.
is now generally available on all plans and in . Instead of storing long-lived provider secrets, your code requests short-lived, scoped tokens at runtime. Deployments authenticate with their existing Vercel OIDC identity. Each token is scoped to the task, refreshed automatically, and expires on its own.Vercel Connectv0
Register a connector . Pass the service name and the CLI pre-populates the brand name, icon, auth type, and MCP or discovery URL, then prompts for any credentials the service requires:once from the CLI
Connect ships with for tools like and , managed connectors for , , , , , and , plus generic OAuth, API key authentication, and MCP servers.100+ preset connectorsNotionWorkdaySlackGitHubLinearSalesforceSnowflakeMicrosoft
Request a token only when your code needs one, with :getToken
Switch the from the app to a named user and the token acts on that user's behalf, triggering the authorization flow when consent is needed.subject
New at GA:
Together with per-environment attachment, including , and one-command revocation, external access becomes something your team can inspect, prove, and cut off in seconds.Custom Environments
Triggers deliver provider events to your app without a stored secret. Vercel Connect verifies signatures server-side, re-attests each event using an OIDC identity, and forwards the event to your project, even when Deployment Protection is enabled.
Connect also manages private keys and the full credential lifecycle, so you get standards-compliant OAuth without building the infrastructure yourself.
Connect works wherever your functions run and is supported in v0, eve, and Chat SDK. Adapters are available for the auth libraries and agent tooling you already use:
The AI SDK adapter authenticates MCP clients with tokens minted at runtime. In this example, the agent gets read-only Linear access issued for a single user, so downstream actions carry that user's identity:
, our open source tool layer for GitHub agents, plugs into eve through Connect via an . Presets like map to Connect scopes automatically, so tokens carry only the permissions the toolset needs:GitHub Toolseve extensioncode-review
Vercel Connect is available on all plans, with pricing based on token requests and trigger events. Hobby includes 500 token requests and 1,000 triggers per month at no additional cost. Pro is billed at $3 per 1,000 token requests and $0.95 per 1,000 triggers, with custom pricing on Enterprise.
Read the and the , or have your coding agent set up Vercel Connect for you with this prompt:documentationlaunch blog post
Any service with one command
Tokens at runtime, not secrets at rest
Access your team can inspect and prove
Triggers without stored webhook secrets
Works with your stack
Pricing and availability
controls who can create and manage connectorsFine-grained RBAC
record authorization and connector activityAudit logs
shows how tokens are used across projectsToken and trigger observability
: Better Auth
@vercel/connect/betterauth: Auth.js
@vercel/connect/authjs: AI SDK
@vercel/connect/ai-sdk: MCP clients
@vercel/connect/mcp: eve
@vercel/connect/eve: Chat SDK
@vercel/connect/chat
Securely connect your AI SDK agents to MCP servers
Give your GitHub agents only the access they need
Source: original entry ↗
More from Vercel
Follow Vercel to get its new changes in your feed and email digest.
Nemotron 3.5 Lightning now available on AI Gateway for free
Nemotron 3.5 Lightning, an open-weight 30B parameter reasoning model from NVIDIA, is now available for free on AI Gateway. The model supports long-running agents, chatbots, and RAG systems with a 1M token context window, tool calling, and structured outputs, accessible via multiple APIs and coding agents.
Gemini 4 Argon now available on AI Gateway
Google's Gemini 4 Argon model is now available through Vercel's AI Gateway with support for coding, agentic work, and complex reasoning tasks. The model features a 1M token context window, multimodal input capabilities (text, image, PDF, video), tool calling, and configurable thinking levels for enhanced performance.
Repository checkout and Git LFS downloads are now faster
Repository checkout and Git LFS downloads are now faster on Vercel, reducing build preparation time. Average checkout time improved by 20%, with LFS-enabled projects seeing a 54% improvement and saving approximately 13 seconds per deployment.