This is a remote MCP server that connects Claude to a hosted Revit conversion and BIM query service. It exposes nine tools for uploading RVT files from URLs, converting them to XKT for web viewing or exporting to IFC and DWG, and querying building data through natural language. You can ask how many walls are in a model, inspect element properties like materials and dimensions, or trigger conversions and get back viewer links without installing Revit locally. Built by Labs Future, it runs over streamable HTTP and requires an API key from their platform. Useful if you need to let Claude work directly with Revit files for quick conversions, BIM data extraction, or sharing 3D models in the browser.
AI-powered BIM tool — convert Revit .rvt files to XKT, IFC and DWG, query model data, and explore building elements through natural language, right inside Claude.
Built by Labs Future · Powered by the Model Context Protocol

The Revit Converter MCP is a remote MCP server that connects Claude (or any MCP-compatible AI client) directly to a Revit file conversion and BIM query service. Once configured, you can:
.rvt files by a public URLNo plugins, no Revit installation needed on the client side.
| Tool | Description |
|---|---|
list_models | List all models stored on the server |
upload_model | Upload a .rvt file from a URL or path |
set_current_model | Set the active model for subsequent operations |
convert_revit_to_xkt | Convert the current model to XKT for 3D web viewing |
get_conversion_status | Check the progress of an ongoing conversion |
export_model | Export the model to IFC or DWG format |
get_export_status | Check export progress and get the download link |
query_model | Query BIM data (element counts, types, filters) |
search_elements | Search and retrieve properties of specific elements |
More tools are on the way — including data audit, workflow automation, optimizing design and deeper BIM data analysis, even model updating. Follow labsfuture.com for updates.
Sign up at labsfuture.com and navigate to your account dashboard.

Demo keys start with
dk_. Full API keys start withsk_.
Open your Claude Desktop configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.jsonAdd the following entry under mcpServers:
{
"mcpServers": {
"revit-converter": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://labsaps-d35810f00db3.herokuapp.com/mcp",
"--header",
"Authorization: Bearer labsfuture.comFreeDemo_MCPKey"
]
}
}
}
Replace the Bearer token with your own key from labsfuture.com. The key above is a shared demo key — get your own for personal model storage and full conversions.

Requires Node.js — npx must be available in your PATH. Install from nodejs.org if needed.
After saving the config, restart Claude Desktop. Open Settings → Connectors and you should see revit-converter listed with 9 tools available.

Once connected, just talk to Claude naturally:
Upload a model
Could you upload this model to the revit converter server?
https://www.dropbox.com/scl/fi/yourfile.rvt?dl=0

List models on the server
Lists all models on the server by name

Convert to XKT and view in browser
yes, convert rac_basic_sample_project.rvt to xkt

Claude returns a direct viewer link — open it to see your model rendered in 3D:

Export to IFC or DWG
export the current model to IFC
Claude triggers the export job and checks back automatically — when ready, it returns a direct download link valid for 60 minutes.
Query BIM data
how many walls in this model?

Inspect element properties
yes, just show me properties of a random wall

LabsFuture builds AI-native tools for the AEC industry. The Revit Converter MCP is part of a broader platform that brings BIM workflows into the age of conversational AI — letting architects, engineers, and developers interact with building data through natural language.
Visit www.labsfuture.com to:
npx mcp-remote)See LICENSE for details.
com.mcparmory/google-sheets
domdomegg/google-sheets-mcp
henilcalagiya/google-sheets-mcp
cct15/war-dashboard-data
moooonad/mcp-google-sheets-full
io.github.br0ski777/csv-to-json