revit-mcp
Revit integration via Autodesk Platform Services — Extract elements, parameters, run schedules, detect clashes, export IFC.
README
Revit MCP
Revit integration via Autodesk Platform Services — Extract elements, parameters, run schedules, detect clashes, export IFC.
Tools (8)
| Tool | Description |
|---|---|
revit_upload |
Upload Revit file to APS and translate |
revit_get_elements |
Get elements by category |
revit_get_parameters |
Get element parameters |
revit_run_schedule |
Extract schedule data |
revit_clash_detect |
Clash detection with VDC rules |
revit_export_ifc |
Export model as IFC |
revit_get_sheets |
List all sheets |
revit_get_views |
List all views |
Quick Start
{
"mcpServers": {
"revit": {
"url": "https://revit-mcp.itmartin24.workers.dev/mcp"
}
}
}
Architecture
- Runtime: Cloudflare Workers
- Auth: APS OAuth2 (client_credentials)
- Database: Cloudflare D1 (usage logging)
- Cache: Cloudflare KV (token caching)
Part of ScanBIM Labs AEC MCP Ecosystem
MIT — ScanBIM Labs LLC
Authentication
Two accepted header formats. Use one, do NOT mix:
x-scanbim-api-key: <your_user_key>— value is the user_key verbatim.Authorization: Bearer sk_scanbim_<your_user_key>— value is the entire string including thesk_scanbim_prefix; the D1user_keycolumn must match this full string.
Mixing formats auto-creates a fresh free-plan row for the alternate key (you'll silently get a new 50-credit account on each switch).
Get your user_key at scanbim.app/settings/billing.
Example
curl -X POST https://mcp.scanbimlabs.io/unified/mcp \
-H "content-type: application/json" \
-H "x-scanbim-api-key: $SCANBIM_USER_KEY" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"list_models","arguments":{}}}'
Response codes
200— tool call proceeded; credits debited.401— missing or malformed auth header (middleware returns JSON-RPC error code-32001).402— insufficient credits; response body includescheckout_urlsfor all 5 credit packs andtop_up_urlfor the billing page.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.