Vercel Connector for AI Agents

Tools your devops agent reaches for on Vercel, scoped per user.

CALL ANY TOOL

List and inspect deployments, retrieve build logs, browse projects, and check domain status.

vercel_alias_create

Create alias

Assigns an alias (custom domain) to a Vercel deployment.

Parameters

Name

Type

Required

Description

alias

string

Required

The alias hostname to assign.

deployment_id

string

Required

The deployment ID to assign the alias to.

team_id

string

Optional

Team ID if the deployment belongs to a team.

vercel_alias_delete

Delete alias

vercel_alias_get

Get alias

vercel_aliases_list

List aliases

vercel_check_create

Create check

vercel_check_update

Update check

vercel_checks_list

List checks

vercel_deployment_cancel

Cancel deployment

vercel_deployment_files_list

List deployment files

vercel_deployment_runtime_logs_get

Get deployment runtime logs

vercel_domain_add

Add domain

vercel_domain_claim

Domain claim

vercel_domain_delete

Delete domain

vercel_domain_verification_get

Get domain verification

vercel_domains_list

List domains

vercel_drain_create

Create drain

vercel_drain_update

Update drain

vercel_edge_config_item_get

Get edge config item

vercel_edge_config_token_create

Create edge config token

vercel_edge_config_tokens_delete

Delete edge config tokens

vercel_edge_configs_list

List edge configs

vercel_project_checks_list

List project checks

vercel_project_domain_delete

Delete project domain

vercel_project_domain_verify

Verify project domain

vercel_project_rollback

Project rollback

vercel_project_update

Update project

vercel_projects_list

List projects

vercel_sandbox_create

Create sandbox

vercel_team_get

Get team

vercel_team_member_remove

Remove team member

For more tools, view docs.

Build your Agent

Drop the toolkit in, point it at the user, and your devops agent can use Vercel from the first run.

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["vercel"], toolNames: ["vercel_deployments_list", "vercel_deployment_get", "vercel_projects_list"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["vercel"], toolNames: ["vercel_deployments_list", "vercel_deployment_get", "vercel_projects_list"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["vercel"], toolNames: ["vercel_deployments_list", "vercel_deployment_get", "vercel_projects_list"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/vercel",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your agent to start using Vercel.

Deployments

Copy the prompt

Copied

List all failed deployments today.

Copy the prompt

Copied

Get build logs for deployment [id].

Copy the prompt

Copied

Which deployments are currently building?

Copy the prompt

Copied

Get details for the latest production deployment of [project].

Projects & domains

Copy the prompt

Copied

List all Vercel projects.

Copy the prompt

Copied

Which projects deployed in the last hour?

Copy the prompt

Copied

List all custom domains.

Copy the prompt

Copied

Which domains have SSL issues?

Debugging

Copy the prompt

Copied

Get error logs for failed deployment [id].

Copy the prompt

Copied

Why did [project] deployment fail?

Copy the prompt

Copied

List deployments with build errors this week.

Copy the prompt

Copied

Get runtime logs for [deployment id].

SEE HOW AUTH WORKS

Users authorize Vercel once. Their credentials stay vaulted, every call is checked, and every action is logged.

Authorize

Your user connects

Vercel

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Vercel

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Vercel

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Vercel

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

Same per-user auth pattern across other devops agents and MCP connectors. Working code, live demos, fork what fits.

Engineering Teams

DevOps assistant agent

Polls GitHub for failing checks and stale PRs, opens Linear issues for the ones that need work, and posts a daily digest to Slack. It acts as the engineer, not a shared service account.

Engineering Teams

Engineering standup agent

Pulls commits from GitHub and GitLab, tracks issue movement in Jira, and posts a per-engineer standup brief to Slack. Each engineer's activity is read on their own delegated OAuth.

Engineering Teams

Auto release notes agent

Reads merged GitHub PRs, groups them into structured release notes, publishes the page to Notion, and announces the release in Slack. Every call runs on the engineer's own delegated OAuth.

Engineering Teams

Slack triage

Polls Slack for new messages, classifies bugs and support requests with a LangGraph router, files GitHub issues or Zendesk tickets, and confirms in the thread.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.

// shared token
 audit → bot_service_account
 user_filter → broken

 // scalekit
 audit → user_abc
 scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Vercel today. Others tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Vercel as the user or as a shared key?

As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Vercel OAuth token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Vercel?

Yes. Pass a tool name filter to listScopedTools so the DevOps agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Vercel.

What happens when a user revokes Vercel access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Can the agent trigger a new deployment or rollback?

Read and inspect operations work out of the box. Triggering deployments or rollbacks requires the authorizing user to have the appropriate Vercel team permissions. Limit the agent to read-only tools if write access is not needed.

How do I build a Vercel agent?

Follow the step-by-step tutorial: Build a Vercel Agent with Claude SDK for Deployment Health. It covers per-user auth, tool scoping, and working agent code for Vercel.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit