Builder.io connector for AI agents

Tools your content agent reaches for on Builder.io, scoped per user.

CALL ANY TOOL

22 tools for your headless CMS in Builder.io: read published content by model or URL, create, update, replace, and delete entries, manage models and content folders, and list and organize media assets.

builderio_asset_delete

Delete asset

Delete a media asset from the Builder space through the Admin API. Returns true when the asset is removed. Use this only when the file is no longer referenced by any content. Use builderio_assets_list to find the asset ID.

Parameters

Name

Type

Required

Description

asset_id

string

Required

ID of the asset to delete.

builderio_asset_folder_create

Create asset folder

builderio_assets_list

List assets

builderio_content_get

Get content

builderio_content_get_by_url

Content get by url

builderio_content_list

List content

builderio_entry_create

Create entry

builderio_entry_delete

Delete entry

builderio_entry_replace

Entry replace

builderio_entry_update

Update entry

builderio_folder_create

Create folder

builderio_folder_delete

Delete folder

builderio_folder_get

Get folder

builderio_folder_update

Update folder

builderio_folders_list

List folders

builderio_model_create

Create model

builderio_model_delete

Delete model

builderio_model_get

Get model

builderio_model_update

Update model

builderio_models_list

List models

builderio_settings_get

Get settings

builderio_users_list

List users

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Builder.io tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["builderio"], toolNames: [
    "builderio_content_get_by_url",
    "builderio_content_list",
    "builderio_entry_update"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Update the hero headline on the pricing page entry" }] });

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

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["builderio"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Update the hero headline on the pricing page entry" }],
  tools,
});

// Execute the tool call with the user's vaulted Builder.io access token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

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

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["builderio"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Update the hero headline on the pricing page entry" }],
  tools,
});

// Tool call runs with the user's vaulted Builder.io access token
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["builderio"] }, pageSize: 100,
});

const agent = new Agent({
  name: "content_agent",
  model: "gemini-2.5-pro",
  instruction: "Builder.io tools scoped to this user",
  tools,
});

await agent.run("Update the hero headline on the pricing page entry");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Builder.io tool. Click to copy, paste into your agent, done.

Content

Copy the prompt

Copied

What content is published at /pricing?

Copy the prompt

Copied

List the latest 10 entries in the blog-article model.

Copy the prompt

Copied

Update the hero headline on the homepage entry to Plans for every team.

Models

Copy the prompt

Copied

List every model in our Builder space.

Copy the prompt

Copied

Show the fields on the blog-article model.

Copy the prompt

Copied

Create a data model called announcement with title and body fields.

Folders and assets

Copy the prompt

Copied

List the content folders in our space.

Copy the prompt

Copied

Create a folder called Q4 Campaigns.

Copy the prompt

Copied

List media assets uploaded this month.

SEE HOW AUTH WORKS

Each user connects their own Builder.io access token once, and Scalekit sends it with every call. Access tokens stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Builder.io

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

Builder.io

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

Builder.io

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

Builder.io

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

See the same per-user auth pattern across other developer and design connectors.

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

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.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Builder.io access token looks fine in a demo. In production every entry and model change looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Builder.io today. Ten connectors 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 Builder.io as the user or through a shared access token?

As the user. Each user connects their own Builder.io access token once, and Scalekit sends it with every call. Audit logs attribute every entry and model change to that user, not a shared service account.

Where is the Builder.io access token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new access token. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Builder.io?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example the content read tools without builderio_entry_delete or builderio_model_delete. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Builder.io 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.

Does the agent see drafts or only published content?

The content read tools, such as builderio_content_list and builderio_content_get_by_url, return published entries through the Builder Content API. Writes such as builderio_entry_create and builderio_entry_update go through the Write API, and models, folders, and assets go through the Admin API.