Provides access to Autodesk Construction Cloud Build, enabling management of construction issues, RFIs, submittals, photos, forms, costs, and documents through natural language interaction with the platform's API.
Autodesk Build MCP Server
A Model Context Protocol (MCP) server implementation for Autodesk Construction Cloud Build, enabling AI-powered construction project management through Claude and other MCP-compatible clients.
Table of Contents
- Overview
- Features
- Architecture
- Prerequisites
- Installation
- Configuration
- Usage
- Available Tools
- API Reference
- Examples
- Development
- Contributing
- License
Overview
This MCP server provides a bridge between AI assistants (like Claude) and Autodesk Construction Cloud Build, allowing you to:
- Manage construction issues, RFIs, and submittals through natural language
- Access and organize project photos and documents
- Track project costs and budgets
- Manage forms and quality control processes
- Automate routine project management tasks
The server implements the Model Context Protocol, making it compatible with any MCP-enabled AI client.
Features
Core Capabilities
- Issue Management: Create, update, and track construction issues
- RFI Management: Submit and respond to Requests for Information
- Submittal Tracking: Manage submittal logs and approval workflows
- Photo Management: Access and organize jobsite photos with location tagging
- Forms & Checklists: Access standardized quality and safety inspection forms
- Cost Management: Track budgets, change orders, and payment applications
- Document Management: Search and retrieve project documents
- Location Management: Manage building areas and location hierarchies
Technical Features
- OAuth2 authentication with token management
- Rate limiting and retry logic
- Comprehensive error handling
- Webhook support for real-time updates
- Batch operations for improved performance
- Caching for frequently accessed data
Architecture
Component Overview
- MCP Server Core: Handles protocol communication and tool routing
- Authentication Module: Manages OAuth2 flow and token refresh
- Tool Handlers: Individual handlers for each Autodesk Build feature
- Cache Layer: Reduces API calls for frequently accessed data
- Error Handler: Provides meaningful error messages and recovery
Prerequisites
- Node.js 18.0 or higher
- npm or yarn package manager
- Autodesk Platform Services account
- Autodesk Construction Cloud Build project access
- OAuth2 application credentials from Autodesk
Installation
Quick Start
Installing as a Package
Configuration
1. Autodesk App Registration
- Visit Autodesk Platform Services
- Create a new app or use existing credentials
- Add the following redirect URI:
http://localhost:3000/callback
- Note your Client ID and Client Secret
2. Environment Variables
Create a .env
file with the following:
3. Claude Desktop Configuration
Add to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Usage
Basic Commands
Once configured, you can use natural language commands with Claude:
Authentication Flow
On first use:
- The server will provide an authentication URL
- Open the URL in your browser
- Log in with your Autodesk account
- Authorize the application
- The server will store the refresh token for future use
Available Tools
Project Management
Tool | Description |
---|---|
list_projects | List all accessible projects |
get_project | Get detailed project information |
search_projects | Search projects by name or criteria |
Issues
Tool | Description |
---|---|
list_issues | List issues with filtering options |
create_issue | Create a new issue |
update_issue | Update existing issue |
close_issue | Close an issue with resolution |
add_issue_comment | Add comment to an issue |
attach_photo_to_issue | Attach photos to issues |
RFIs (Requests for Information)
Tool | Description |
---|---|
list_rfis | List RFIs with status filters |
create_rfi | Create a new RFI |
respond_to_rfi | Submit RFI response |
update_rfi_status | Update RFI status |
get_rfi_details | Get detailed RFI information |
Submittals
Tool | Description |
---|---|
list_submittals | List submittal items |
create_submittal | Create new submittal |
update_submittal_status | Update submittal status |
add_submittal_revision | Add revision to submittal |
Photos
Tool | Description |
---|---|
list_photos | List project photos |
get_photo_details | Get photo metadata |
search_photos_by_location | Find photos by location |
search_photos_by_date | Find photos by date range |
Forms & Checklists
Tool | Description |
---|---|
list_forms | List available forms |
get_form_responses | Get submitted forms |
search_forms | Search forms by type/status |
Cost Management
Tool | Description |
---|---|
get_budget_summary | Get project budget overview |
list_change_orders | List change orders |
get_cost_trends | Get cost trend analysis |
API Reference
For detailed API documentation, see docs/api-reference.md
Examples
Example 1: Issue Management Workflow
Example 2: RFI Workflow
More examples in examples/ directory.
Development
Project Structure
Running Tests
Debugging
Enable debug logging:
Building for Production
Contributing
We welcome contributions! Please see CONTRIBUTING.md for guidelines.
Development Workflow
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature
) - Commit your changes (
git commit -m 'Add amazing feature'
) - Push to the branch (
git push origin feature/amazing-feature
) - Open a Pull Request
Code Style
- Use ES6+ features
- Follow ESLint configuration
- Add JSDoc comments for all public functions
- Write tests for new features
Troubleshooting
Common Issues
Authentication Errors
- Ensure your Autodesk app has the correct permissions
- Check that redirect URI matches exactly
- Verify client ID and secret are correct
Connection Issues
- Check firewall settings
- Verify internet connectivity
- Ensure Autodesk services are accessible
Rate Limiting
- The server implements automatic retry with backoff
- Consider enabling caching for frequently accessed data
For more help, see docs/troubleshooting.md
Security
- Credentials are stored securely using system keychain when available
- All API communications use HTTPS
- OAuth2 tokens are refreshed automatically
- Sensitive data is never logged
See SECURITY.md for security policies.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgments
- Anthropic for the Model Context Protocol
- Autodesk Platform Services team
- MCP community for examples and best practices
Support
- 📧 Email: support@example.com
- 💬 Discord: Join our server
- 🐛 Issues: GitHub Issues
- 📖 Docs: Full Documentation
This server cannot be installed
A Model Context Protocol server implementation for Autodesk Construction Cloud Build that enables AI assistants to manage construction issues, RFIs, submittals, photos, forms, and costs through natural language.
Related MCP Servers
- AsecurityAlicenseAqualityA Model Context Protocol server that enables AI assistants to interact with Jenkins CI/CD servers, providing tools to check build statuses, trigger builds, and retrieve build logs.Last updated -310JavaScriptMIT License
- -securityFlicense-qualityA Model Context Protocol server implementation that enables AI assistants to interact with Linear project management systems, allowing them to create, retrieve, and modify data related to issues, projects, teams, and users.Last updated -153TypeScript
Plane MCP Serverofficial
AsecurityAlicenseAqualityA Model Context Protocol server that enables AI interfaces to seamlessly interact with Plane's project management system, allowing management of projects, issues, states, and other work items through a standardized API.Last updated -4661950TypeScriptMIT License- AsecurityFlicenseAqualityA Model Context Protocol server that enables AI assistants to interact with Azure DevOps services, providing capabilities for work item management, project management, and team collaboration through natural language.Last updated -21Python