MCP Connector for Navisworks

What it does

A Navisworks add-in that lets your existing AI assistant read and interrogate the model that is open on the user's machine, including clash results, and in the Pro edition author review content such as clash tests, saved viewpoints and selection sets. You bring your own AI subscription. Supported on Navisworks 2022 to 2027.

How edits are controlled

The AI does not have unattended access to the model. Every tool call is initiated from the AI client by the user, in a session the user is watching.

The free tier is read-only. Its tools interrogate the model, its properties and its clash results, and can move the camera, but cannot change or save the file.

Pro tools can author review content in the open file: selection and search sets, saved viewpoints, comments, clash tests and results, TimeLiner tasks and appearance overrides. Those changes run inside named Navisworks transactions and appear in the Navisworks undo history, and a failed operation is discarded rather than committed. Appending a model, opening or starting a new document, and setting the background sit outside that mechanism.

No tool in any edition writes back to the source models appended to the scene. Exports go to a path named in the call. The connector never saves the open file on its own: saving happens only through the tool whose purpose is to save, and opening or starting a new document requires the call to confirm that unsaved changes may be discarded.

Where model data goes

To whichever AI provider you already use, under your existing contract with that provider. AUTOM8LABS never receives your model data, never stores it, and is not a processor of it.

The add-in runs inside Navisworks on the workstation. The component that talks to your AI client makes no outbound network connections of its own.

What AUTOM8LABS receives

The machine identifier is a SHA-256 hash of hardware values. The underlying hardware identifiers never leave the machine.

What is stored

On the workstation

• No listening port. The add-in communicates with your AI client over a Windows named pipe, not a network socket.
• Access restricted to the same Windows user. The pipe is scoped to the account Navisworks is running under, and no other account on the machine can open it. A pipe that cannot be scoped that way is never created.
• No log file by default. Diagnostics are off unless a user enables them for troubleshooting. When enabled, the log records lifecycle and licence events, and it never leaves the machine.
• Stored credentials are encrypted. The licence and entitlement caches are protected with Windows DPAPI.
• No elevated privileges are required at runtime.

Supply chain

The add-in ships a single third-party .NET component, a widely used JSON library from the official NuGet ecosystem, under the MIT licence.

The component that talks to your AI client is a self-contained executable built on a pinned Node.js runtime. Its own dependency set is MIT, ISC or BSD licensed. There are no copyleft licences in the shipped product.

A CycloneDX Software Bill of Materials is produced for each supported Navisworks version, and a further one for the bridge executable. At version 1.0.8 no shipped component on either side carries a known vulnerability, and the build fails if that stops being true.

SBOMs are available on request from security@autom8labs.io.

Assurance

Every binary and installer is code-signed as AUTOM8LABS LTD through Azure Trusted Signing.

See the Trust Center for the full assurance position and the sub-processor list.