Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@OpenStudio MCP Serverload the office building model and show me the thermal zones"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
OpenStudio MCP Server
A Model Context Protocol (MCP) server that enables AI assistants like Claude to interact with OpenStudio building energy models. Load, inspect, and manipulate OpenStudio Model (OSM) files through a comprehensive set of tools accessible via natural language.
Credits and Acknowledgments
This project is heavily based on the EnergyPlus MCP Server developed by LBNL-ETA (Lawrence Berkeley National Laboratory - Energy Technologies Area). The server architecture, tool structure, and implementation patterns have been replicated as closely as possible from their excellent work.
The tools in this server are built using the OpenStudio-Toolkit library, which provides Python interfaces to OpenStudio's building modeling capabilities.
This project was developed with the invaluable assistance of Claude Code powered by Anthropic's Claude Sonnet 4.5.
Features
Available Tools (20+)
π File & Model Management
load_osm_model- Load OpenStudio Model files with intelligent path resolutionsave_osm_model- Save modified modelsconvert_to_idf- Export to EnergyPlus IDF formatcopy_file- Copy files with fuzzy matching and smart discoveryget_model_summary- Get comprehensive model statisticsget_building_info- Get building object details
π Visualization & Analysis
apply_view_model- Generate interactive HTML visualization (geometry, HVAC, zones, materials)apply_space_type_and_construction_set_wizard- Apply ASHRAE 90.1 building templates
ποΈ Building Geometry
list_spaces- List all spaces with propertiesget_space_details- Get detailed information about a specific spacelist_thermal_zones- List all thermal zonesget_thermal_zone_details- Get detailed zone information
π§± Materials & Constructions
list_materials- List all materials with thermal properties
π HVAC Systems
list_air_loops- List all air loop HVAC systems
π‘ Internal Loads
list_people_loads- List occupancy loadslist_lighting_loads- List lighting power densitieslist_electric_equipment- List equipment loads
π Schedules
list_schedule_rulesets- List all schedule rulesets
βοΈ Server Management
get_server_info- Get server configuration and statusget_current_model_status- Check currently loaded model
Key Capabilities
Intelligent File Discovery: Automatically finds files in multiple locations including Claude Desktop uploads
Fuzzy Matching: Finds files even with partial names or typos
Dual Environment Support: Works seamlessly in both Docker and Claude Desktop
Comprehensive API: Covers building geometry, HVAC, loads, materials, and schedules
Installation
Prerequisites
Docker Desktop (REQUIRED - recommended installation method)
Claude Desktop, VS Code, or Cursor (for AI assistant integration)
Windows/Mac/Linux system
Quick Start (Docker - Recommended)
1. Clone the Repository
2. Build Docker Image
This builds a container with:
Python 3.12
OpenStudio 3.7.0 (system installation with SDK and Python bindings)
All required dependencies
OpenStudio-Toolkit library
Verify Build:
3. Configure Claude Desktop
Edit your Claude Desktop configuration file:
Windows: %APPDATA%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Add this configuration (Windows example):
π‘ Windows Setup Tip (Best Practice):
We strongly recommend cloning this repository to a short root path like
C:\openstudio-mcp-serverinstead of deep user directories likeC:\Users\YourName\Documents\GitHub\openstudio-mcp-server.Why? Windows has a 260-character path limit that can cause issues with nested project directories and long dependency paths. This recommendation follows EnergyPlus best practices for avoiding path-related build and runtime errors.
Example:
β Recommended:
C:\openstudio-mcp-serverβ οΈ Avoid:
C:\Users\YourName\Documents\Projects\BuildingEnergy\openstudio-mcp-server
CRITICAL: The configuration requires two volume mounts (see explanations below):
-v C:\\:/mnt/c- Grants access to your C: drive for reading/writing model files-v C:\\PATH\\TO\\YOUR\\openstudio-mcp-server:/workspace- Mounts the server source code
Important: Replace C:\\PATH\\TO\\YOUR\\openstudio-mcp-server with your actual repository path.
π Outputs Directory:
Generated files (HTML visualizations, IDF exports, reports) are automatically saved to
openstudio-mcp-server/outputs/inside the container, which maps toC:\openstudio-mcp-server\outputs\on your host machine through the workspace volume mount. The server creates this directory automatically with proper permissions.
π For detailed setup instructions, see
4. Restart Claude Desktop
Close and reopen Claude Desktop to load the MCP server.
5. Verify Installation
In Claude Desktop, ask:
Claude should list all available tools.
File Access (CRITICAL)
Understanding Docker Volume Mounts
The OpenStudio MCP Server runs inside a Docker container, which has its own isolated filesystem. To access files on your host machine (your computer), you must use mounted paths.
The configuration requires two separate volume mounts, each serving a distinct purpose:
1. C: Drive Access Mount: -v C:\:/mnt/c
Purpose: Grants the server Read/Write access to your entire C: drive, enabling it to load models from and save outputs to your host machine.
This means:
Files on your C: drive are accessible at
/mnt/c/...pathsOutputs saved to
/mnt/c/...persist on your host machineWithout this mount, the container cannot access your files
2. Server Source Code Mount: -v C:\PATH\TO\YOUR\openstudio-mcp-server:/workspace
Purpose: Mounts the server's source code (the cloned repository) into the container at /workspace, enabling the container to execute the Python server.
This means:
The server can access its own code, dependencies, and sample files
Changes to server code on your host are reflected in the container
Replace the placeholder path with where you actually cloned the repository
How to Reference Files
β WRONG (Host Paths)
β CORRECT (Container Paths)
Common Path Mappings
Your Folder (Windows) | Container Path |
|
|
|
|
|
|
|
|
Project samples |
|
Example Usage
Load a model from Downloads:
Convert and save to Documents:
Why This Matters:
β Files at
/mnt/c/...paths persist after container stopsβ Files saved to
/tmp/...or/workspace/...(without/mnt/c) are lost
π For complete file access documentation, see
Usage
Basic Workflow
Place your OSM file in the
sample_files/models/directoryAsk Claude to work with it:
"Load R2F-Office-Hub-006.osm and tell me about the building"Claude will:
Load the model using
load_osm_modelExtract information using
get_model_summary,list_spaces, etc.Present the results in natural language
Example Conversations
Analyze a Building
Export to EnergyPlus
Compare Spaces
Working with Uploaded Files
Claude Desktop can handle files you upload directly:
Upload your
.osmfile in the chatAsk Claude to analyze it
The server automatically finds and loads it from Claude's upload directory
Project Structure
Documentation
CLAUDE_DESKTOP_SETUP.md - β Golden Docker configuration for Claude Desktop
TESTING_PROTOCOL.md - Standard testing procedures and troubleshooting
USER_GUIDE.md - Simple guide for end users (includes smart path handling)
DEVELOPER_NOTES.md - Technical implementation details
How It Works
Architecture
Tool Execution Flow
User asks: "How many spaces are in this building?"
Claude selects tool:
list_spaces()Server executes:
Checks if model is loaded
Calls OpenStudio-Toolkit function
Extracts space data into DataFrame
Converts to JSON
Returns to Claude:
{"status": "success", "count": 12, "spaces": [...]}Claude responds: "This building has 12 spaces..."
Development
Adding New Tools
See DEVELOPER_NOTES.md for detailed instructions on:
Adding new MCP tools
Integrating OpenStudio-Toolkit functions
Error handling patterns
Testing procedures
Running Tests
Local Development
Troubleshooting
"Model not loaded" Error
Ensure you've loaded a model first with
load_osm_modelCheck that the file is in
sample_files/models/
"File not found" Error
Verify the file path is correct
Check file is in mounted workspace directory
Try using just the filename (server will search automatically)
Claude Doesn't Use Tools
Verify MCP server is connected (check Claude Desktop status bar)
Restart Claude Desktop
Check server logs in
logs/openstudio_mcp_server.log
Docker Issues
Ensure Docker Desktop is running
Verify volume mount path is correct and absolute
Check Docker image was built successfully
"ModuleNotFoundError: No module named 'openstudio'" Error
This means the OpenStudio Python bindings are not installed. This should not happen with the Docker image, but if you're running locally:
Note: The Docker image automatically installs this package during build.
Roadmap
Future enhancements planned:
Model Modification: Tools to create and modify spaces, zones, surfaces
Advanced HVAC: Detailed HVAC component inspection and editing
Simulation: Execute EnergyPlus simulations
Results Analysis: Parse and visualize simulation results
Parametric Studies: Automated parametric analysis workflows
Geometry Tools: Create building geometry from scratch
Contributing
Contributions are welcome! Please:
Fork the repository
Create a feature branch
Make your changes
Add tests if applicable
Submit a pull request
License
MIT License - See LICENSE file for details
Acknowledgments
LBNL-ETA for the EnergyPlus MCP Server architecture that served as the foundation for this project
OpenStudio-Toolkit for providing the Python interface to OpenStudio
NREL for developing and maintaining the OpenStudio SDK
Anthropic for Claude and Claude Code (Sonnet 4.5)
Model Context Protocol community for the MCP specification
Support
Issues: GitHub Issues
Discussions: GitHub Discussions
OpenStudio Documentation: https://openstudio.net/
Built with β€οΈ using Claude Code, Python and OpenStudio