Automatización MCP — Navisworks Manage 2025
MCP server to control Autodesk Navisworks Manage 2025 from Claude via natural language, enabling model inspection, property search, selection sets, and clash detection.
README
<div align="center">
</div>
Automatización MCP — Navisworks Manage 2025
Servidor Model Context Protocol que permite controlar Autodesk Navisworks Manage 2025 desde Claude en lenguaje natural: inspección de modelos federados, árbol del modelo, búsqueda por propiedades, selection sets y detección de conflictos (clash).
Arquitectura
Claude
↕ stdio (MCP)
server.py ← FastMCP, define los @mcp.tool()
└─ tools/plugin_bridge.py ← cliente TCP → localhost:65433
↓
plugin/Navisworks_MCP_Plugin.dll ← plugin C# DENTRO de Navisworks
↓ API .NET de Navisworks
Navisworks Manage 2025
Diferencia clave con Civil 3D: Navisworks no expone COM accesible desde Python. El plugin C# es el único camino — si no está cargado, las herramientas devuelven error. Verifica siempre con
navis_ping()antes de ejecutar comandos.
Estructura
server.py ← servidor MCP (punto de entrada)
app.py ← aplicación auxiliar
requirements.txt ← dependencias Python
tools/ ← model_info, model_tree, property_search, selection_sets, clash, federated_inspector
bim_tools/ ← utilidades BIM (property_search)
plugin/ ← plugin C# (Navisworks_MCP_Plugin.cs) + botones + bundle
instalar_plugin.bat ← instalación del bundle
Instalación
Servidor MCP
pip install -r requirements.txt
python server.py
Plugin C# (necesario)
cd plugin
dotnet build -c Release
Instala el bundle (auto-carga al abrir Navisworks) copiando plugin/bundle/ a
%AppData%\Autodesk\ApplicationPlugins\Navisworks_MCP_Plugin.bundle\
(o usa instalar_plugin.bat). También se puede cargar manualmente en
Add-Ins → External → "MCP Server".
Probar la conexión
import socket, json
s = socket.socket(); s.connect(('127.0.0.1', 65433))
s.sendall(json.dumps({'command':'PING','params':{}}).encode())
print(s.recv(4096).decode()); s.close()
Licencia
Ver LICENSE. Autodesk y Navisworks son marcas de Autodesk, Inc. Proyecto no afiliado a Autodesk.
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.