mcpField
A
ai-connector-for-revit

ai-connector-for-revit

Local
nonica.ioMedia & Design19Updated 3w ago

About ai-connector-for-revit

AI Connector for Revit connects MCP-compatible desktop apps to live Revit models through more than 50 predefined tools. It is for Revit users who want AI apps to inspect, select, edit, and document model elements without generating Revit code.

Key features

  1. 01More than 50 predefined tools
  2. 02Inspect model elements and parameters
  3. 03Edit elements and properties
  4. 04Create sheets, sections, and views
  5. 05Integrates through the NonicaTab toolbar

Use cases

  1. 01Check element parameters and family sizes
  2. 02List views placed on sheets
  3. 03Edit Revit model elements
  4. 04Create sheets or sections

MCP support

It exposes predefined Revit model operations as tools to MCP-compatible desktop apps, including Claude, Cursor, and Copilot in VSCode.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository
Packages
mcpbnonicatabpro.mcpb1.0.19

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

AI Connector for Revit

The AI Connector for Revit connects AI Desktop Apps (like Claude, Cursor or Copilot) with Revit. Rather than generating new Revit code, the AI uses a set of +50 predefined tools to inspect, select, edit and document elements in Revit models.


Features

  • Predefined Tools

    • Inspect and edit parameters, family sizes, sheets and views, names and more
    • Examples:
      • Get the value of a parameter
      • Determine the file size of a family
      • List views placed on a sheet
  • Feedback-Driven Interaction
    The AI invokes your tools and adapts to Revit’s responses, reducing errors from hand-crafted code.

  • Read, Edit and Document in Revit
    Model reading, inspection, and element selection.
    Edit parameters, elements and properties.
    Add views to sheets, create sheets or sections.

  • Integration with Nonicatab
    The “AI Connector” button appears in the Nonicatab toolbar after installation, and selecting the ready-to-use toolbar or tool.


Prerequisites

  • Autodesk Revit from 2022 to 2027
  • NonicaTab Revit plugin.
  • Claude Desktop App or Cursor for automatic setup Also compatible with Copilot in VSCode and any other MCP compatible desktop app.

Installation

  1. Get the installer from Autodesk App Store.

  2. Claude.
    Install Claude Desktop App (read the Terms and Conditions, remember you are granting access to AI models to your Revit model). It is free and enough for a few tests, but you may need Claude pro for frequent use and conversation length.

  3. Run Revit.
    Start Revit (from 2022 to 2027), and select a toolbar that includes the AI Connector for Revit.

  4. Run the AI Connector for Revit.
    Go to Nonicatab toolbar in Revit and run the AI Connector. If Claude was opened, remember to restart Claude (close from corner next to Windows clock) after opening the AI Connector the first time.

  5. Start asking.
    While the AI Connector for Revit is open and active, Claude will be able to access your Revit model using a set of tools.


Tools Overview

A selection of the available micro-tools is listed below. Use Search and Tools in Claude to see full list.

ToolDescription
get_parameters_from_elementid(list_elementId, name)Returns all parameters for the specified element id.
get_size_in_MB_of_families(familyName)Returns the family file sizes in megabytes.
get_viewports_placed_on_sheets(sheetNumber)Lists all views placed on a list of sheets.

Acknowledgements

lisiting01 and Jean Marc Couffin for the first Revit MCP.

Anthropic for Model Context Protocol.

AI service providers for powering the backend and chat interface.


License

Copyright 2026 ©️ All rights reserved Nonica

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.