How is this different from connecting Builder.io MCP directly?

Connected directly, an agent sees every tool the server exposes and holds the credential itself. Through TrustGate you choose which tools each agent gets, and every call is logged against the agent that made it.

What if the Builder.io MCP API changes?

We track the Builder.io MCP schema, so the tool catalogue stays current. Tools you have already allowed keep working, and anything new stays denied until you enable it.

Can I give different agents different Builder.io tools?

Yes. Access is set per agent: one can get a handful of read tools, another the full set. You grant the whole MCP or single tools within it.

Where can I see what my agents did in Builder.io?

Every call is logged against the agent that made it, with the tool it used. Activity can be sent on to your own monitoring.

Do I need to run the Builder.io MCP server myself?

No. TrustGate connects to the Builder.io MCP server and sits in front of it. Your agent only talks to your TrustGate URL, never to Builder.io directly.

Connect Builder.io MCP to your AI agents, securely.

Q: Is Builder.io MCP secure?

The server itself exposes 17 tools, and some of them can write to your Builder.io account. Behind TrustGate an agent only sees the tools you allow, requests and responses are inspected, and every call is logged. Anything outside the allowlist is denied before it reaches Builder.io.

One secured endpoint for every Builder.io call your AI agents make, scoped per user, inspected, and logged.

Get started for free

Get a demo

Try Builder.io MCP now

What your agents can ask once Builder.io MCP is connected.

Select the tools your AI agents can call

17 tools from the Builder.io MCP schema.

Showing 17 tools

Get Builder contentreadRetrieves content entries from a specific model with query filters, for when the criteria are precise: filtering by field values such as names, IDs or other properties.
Browse Builder modelsreadBrowses every content entry within a model with no filters applied, for an overview of what exists before making more targeted queries.
Search Builder contentreadPerforms a text search across all content entries in every model in the Space. It searches published content by default, and drafts on request.
Search content IDsreadA fast two-step search returning matching content IDs and names without pulling full content, for scanning large datasets before fetching details for a handful.
Create Builder contenthigh riskCreates a new content entry in any model, validating fields against the model schema. For page models it generates a URL automatically. Builder's guidance is to be explicit about whether the entry should be published immediately.
Update Builder contenthigh riskModifies an existing content entry and returns links to the Builder editor and the live page. It also changes entry targeting and scheduling parameters.
List Builder modelsreadReturns a complete inventory of the content models available in the current Space.
Get Builder model schemareadRetrieves the detailed schema for a model: field structure, data types, validation rules and relationships.
Create Builder modelwriteCreates a new content model with field types, validation rules and model properties. Models can be of type data, component, page, section or symbol.
Update Builder modelhigh riskModifies an existing model by adding fields, changing field properties, updating validation rules or adjusting settings, which reshapes the schema existing content was written against.
Get design tokensreadRetrieves the design tokens configured in the Space, including colours, spacing values and typography settings.
Get registered componentsreadRetrieves the custom components registered in the Space and available for use in content entries, so generated content references real component names.
Get templatesreadRetrieves the available templates, both user-created and official Builder ones, as a starting point for new content.
Get page hierarchyreadReturns a sitemap-style view of the Space's page structure, showing parent-child relationships, navigation structures and overall site architecture.
Search assetsreadSearches the digital assets stored in the Space, including images, videos, documents and other file types, by filename pattern, asset type and metadata.
Create Symbolhigh riskCreates a reusable Symbol from a block structure. Symbols are automatically published once created, and stay in sync across every page that embeds them.
Get authenticated userreadReturns the currently authenticated user and which Builder Space the MCP session is connected to.

What Builder.io MCP exposes

Builder.io MCP groups its 17 tools into 5 categories, each with a suggested starting policy.

All 17 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Content	Retrieving entries from a model with query filters, browsing every entry in a model unfiltered, text search across all models in the Space, a fast two-step search returning only IDs and names, and creating and updating entries including targeting and scheduling	Read / Write	Creating content can publish it immediately depending on how the request is phrased, and updating content can change targeting and scheduling as well as copy. Require the published flag to be explicit on every write
Models & Schema	A complete inventory of the content models in the Space, the detailed schema for one model with its field structure, data types, validation rules and relationships, and creating or updating models of type data, component, page, section or symbol	Read / Write	Updating a model changes the schema that existing entries were written against. Read the schema first so the agent is editing fields that exist rather than inventing them
Design System	The design tokens configured in the Space including colours, spacing and typography, the custom components registered and available for use in entries, and the available user-created and official Builder templates	Read	Read-only and worth making mandatory before any content write, so generated content references components that actually exist rather than guessed names
Structure & Assets	A sitemap-style view of the page hierarchy with parent-child relationships and navigation structure, search across stored images, videos, documents and other files, and creating a reusable Symbol from a block structure	Read / Write	A Symbol is published automatically on creation and stays in sync wherever it is embedded, so creating one is a live change across every page that uses it
Session	The currently authenticated user and which Builder Space the MCP session is connected to	Read	Low risk and genuinely useful in multi-Space setups: confirm the Space before any content change, since the connection binds to one Space at sign-in

Connect Builder.io MCP to your AI agent

Four steps, under ten minutes.

01
Sign in to NeuralTrust
Open the NeuralTrust platform, sign in and go to Getting started, then Connect your tools.
02
Choose your agent
When asked which agent you use, pick Claude Code, Codex, Cursor, Windsurf, Copilot or your own code.
03
Connect Builder.io
Find Builder.io in the tool list and connect it.
04
Connect your agent
Follow the steps on screen to add the config to your agent, then send the test prompt.

Permissions down to the single tool

You do not allow Builder.io MCP or block it. You allow the exact tools each agent can call, one by one.

Builder.io MCP	17 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 17 tools

Tool by toolConnecting the server is not the unit of access. Each tool is granted on its own.
Default denyA tool you have not enabled is never exposed to the agent.
Approval on writesTools that change or delete things can require a human to confirm.

Is Builder.io MCP secure?

One endpoint instead of raw credentials. Every call is checked against policy and logged.

AI agentsConnect through your MCP client configuration.	NeuralTrustApply controls based on your configuration.	Builder.io MCP17 capabilities documented at mcp.builder.io/mcp/publish over streamable HTTP. Builder names these as capabilities rather than exact tool identifiers, so the names here follow its documentation. OAuth 2.0 with dynamic client registration, bound to one Content or Hybrid Space at sign-in.
Coding assistants	Connection & credentialsper user	Content6 tools
Internal copilots	Tool access policiesdeny by default	Models & Schema4 tools
Workflow automations	Request & response inspectioninline	Design System3 tools
Compatible MCP clients	Activity monitoringalerts and logs	All other tools4 tools