Trimble Connect MCP Server
Exposes structured documentation for 200+ Trimble Connect API endpoints and provides tools for AI-assisted development of Trimble Connect extensions and applications.
README
Trimble Connect MCP Server
MCP (Model Context Protocol) server exposing all Trimble Connect for Browser APIs documentation. Designed for AI-assisted development of Trimble Connect extensions and applications.
What's included
This MCP server provides structured, searchable documentation for 200+ API endpoints across the entire Trimble Connect platform:
| Category | Description |
|---|---|
| Workspace API | SDK connection, namespaces (project, user, extension, ui, viewer, embed), events |
| REST API (Core v2.0) | Projects, files, folders, todos, views, search, regions |
| REST API Extended | Activities, clashes (full CRUD), 2D views, comments, companies, groups, object links, object sync, releases, shares, tags, users, view groups, extended files/folders/projects/views endpoints |
| BCF API | BIM Collaboration Format — topics, comments, viewpoints |
| Viewer 3D API | Camera, selection, objects, models, hierarchy, section planes, icons, layers, point clouds |
| Markup API | Annotations — text, arrows, lines, clouds, measurements, points, freelines |
| View API | Saved 3D views (CRUD via Workspace API) |
| Panels API | PropertyPanel, DataTable, ModelsPanel |
| Authentication | OAuth 2.0, integrated mode (Workspace API), standalone mode, token management |
| Regions | URLs per region (US, EU, APAC, AU) for Core API and BCF API |
| Extensions | Types (project, viewer3d, embedded), manifests, installation guide |
| Property Set Service | Custom property sets for BIM model objects, libraries, definitions, instances |
| Trimble Connect SDK | trimble-connect-sdk npm package — TCPS Client, Organizer (LBS/WBS), PSet SDK, Credentials |
| TypeScript Types | All interfaces (Vector3, Camera, ObjectProperties, BCFTopic, ViewerSelection, etc.) |
| Project Setup | Architecture, folder structure, backend proxy, Vite config, deployment |
| Code Examples | Extension skeletons, React hooks, ViewerBridge pattern, annotation workflow |
| Pitfalls | Common bugs and validated solutions for Trimble Connect extensions |
Available tools
| Tool | Description |
|---|---|
search_trimble_connect_docs |
Full-text search across all documentation |
get_api_reference |
Get complete reference for a specific API category |
get_extension_starter |
Get a starter template for a new extension (project/viewer3d/embedded) |
get_viewer_api_guide |
Get detailed guide for a specific Viewer 3D topic |
list_available_docs |
List all available documentation sections |
tc_bcf_dashboard_app |
MCP App: interactive Trimble Connect BCF dashboard rendered inside Trimble Assist |
tc_bcf_create_app |
MCP App: interactive form to create a BCF topic, rendered inside Trimble Assist (submits via tc_bcf_create_topic) |
MCP Apps (interactive UI in Trimble Assist)
tc_bcf_dashboard_app and tc_bcf_create_app are MCP Apps: they return an HTML resource
(text/html+skybridge) that Trimble Assist renders inline in the chat as a nested iframe.
- The HTML connects to the host via
@modelcontextprotocol/ext-apps(loaded fromhttps://esm.sh). - Initial context is pushed to the app through the tool's
structuredContent. - The create form has two submit paths:
- Without 3D viewpoint: calls the server tool
tc_bcf_create_topicviacallServerTool(immediate, server-side, no duplication of logic). - With current 3D viewpoint (checkbox, default on): calls
sendMessageto ask the agent to create the BCF through the host application'screate_bcf_topictool, which captures the live camera + snapshot + loaded models. This uses only the standard MCP Apps SDK.
- Without 3D viewpoint: calls the server tool
- CSP allow-list (
esm.sh) is declared in the resource_meta.ui.csp.
Note: the Trimble host-proxy extension (
callLocalToolfrom@trimble-agentic/agentic-mcp-app-tools) would let the app call host tools directly, but that package is private (not on public npm/esm.sh), so it cannot be imported into a server-served HTML app. ThesendMessagedelegation above achieves the same outcome (viewpoint capture in the host) using only the public SDK.
Installation
Prerequisites
- Node.js >= 18
- npm
Build from source
git clone https://github.com/YOUR_USERNAME/trb-mcp-server-api.git
cd trb-mcp-server-api
npm install
npm run build
Configuration
Cursor IDE
Add to your Cursor MCP settings (.cursor/mcp.json or global settings):
{
"mcpServers": {
"trimble-connect": {
"command": "node",
"args": ["C:/path/to/trb-mcp-server-api/dist/index.js"]
}
}
}
Claude Desktop
Add to your Claude Desktop config (claude_desktop_config.json):
{
"mcpServers": {
"trimble-connect": {
"command": "node",
"args": ["C:/path/to/trb-mcp-server-api/dist/index.js"]
}
}
}
VS Code (Copilot)
Add to .vscode/mcp.json:
{
"servers": {
"trimble-connect": {
"command": "node",
"args": ["C:/path/to/trb-mcp-server-api/dist/index.js"]
}
}
}
Usage examples
Once configured, the AI assistant can use these tools:
Search for specific API methods:
"Search Trimble Connect docs for viewer selection"
Get a complete API reference:
"Get the viewer-api reference"
Start a new extension project:
"Get the extension starter for a viewer3d extension with React"
Get specific viewer API guide:
"Get the viewer API guide for hierarchy"
List all available docs:
"List all available Trimble Connect documentation"
Project structure
trb-mcp-server-api/
├── src/
│ ├── index.ts # MCP server entry point
│ └── data/ # Structured documentation
│ ├── workspace-api.ts # Workspace API reference
│ ├── rest-api.ts # REST API Core v2.0 (basic)
│ ├── rest-api-extended.ts # REST API extended (activities, clashes, comments, companies, groups, etc.)
│ ├── bcf-api.ts # BCF Topics API
│ ├── viewer-api.ts # Viewer 3D API
│ ├── markup-api.ts # Markup/Annotations API
│ ├── view-api.ts # View API
│ ├── panels-api.ts # PropertyPanel, DataTable, ModelsPanel
│ ├── auth.ts # Authentication (OAuth, tokens)
│ ├── regions.ts # Region URLs
│ ├── extensions.ts # Extension types, manifests, embedded
│ ├── sdk.ts # trimble-connect-sdk (TCPS, Organizer, PSet)
│ ├── typescript-types.ts # TypeScript interfaces
│ ├── project-setup.ts # Architecture, proxy, Vite, deployment
│ ├── code-examples.ts # Code skeletons and patterns
│ ├── property-set.ts # Property Set Service
│ └── pitfalls.ts # Common pitfalls and solutions
├── dist/ # Compiled output
├── package.json
├── tsconfig.json
└── README.md
Updating documentation
To add or update API documentation:
- Edit the relevant file in
src/data/ - Run
npm run build - Restart the MCP server (or reconnect in Cursor)
Source documentation
- Workspace API — npm
- Workspace API — Reference
- Core API — Developer docs
- BCF Topics — Swagger
- Modus 2.0 — Design System
- Developer Portal
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。