Clarity PPM MCP Server
Enables AI assistants to interact with CA Clarity PPM for discovery, CRUD operations, and analytics.
README
Clarity PPM MCP Server
A Model Context Protocol (MCP) server for CA Clarity PPM that enables AI assistants to interact with your Clarity PPM system through a standardized interface.
Features
🔍 Discovery Tools
- clarity_list_objects - Discover all available object types (standard and custom)
- clarity_describe_object - Get detailed metadata about any object
- clarity_get_lookup_values - Retrieve dropdown/lookup values
- clarity_search_metadata - Search objects and fields by name (supports Hebrew!)
📋 CRUD Operations
- clarity_list_records - List records with smart filtering and pagination
- clarity_get_record - Get a single record with all details
- clarity_count_records - Count records matching criteria
- clarity_get_children - Get child records (e.g., tasks under a project)
- clarity_create_record - Create new records
- clarity_update_record - Update existing records
- clarity_delete_record - Delete records
📊 Analytics
- clarity_get_distribution - Get distribution data for visualizations
🔗 Deep Linking
- All records include direct links to open in Clarity UI
- Supports projects, tasks, resources, ideas, and custom objects
Quick Start
1. Install Dependencies
npm install
2. Configure Environment
Copy .env.example to .env and configure:
cp .env.example .env
Edit .env:
CLARITY_BASE_URL=https://your-clarity.com
CLARITY_USERNAME=your_username
CLARITY_PASSWORD=your_password
3. Build
npm run build
4. Run
stdio mode (for Claude Desktop, etc.):
npm start
HTTP mode (for web integrations):
TRANSPORT=http npm start
Configuration for Claude Desktop
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"clarity-ppm": {
"command": "node",
"args": ["/path/to/clarity-ppm-mcp-server/dist/index.js"],
"env": {
"CLARITY_BASE_URL": "https://your-clarity.com",
"CLARITY_USERNAME": "your_username",
"CLARITY_PASSWORD": "your_password"
}
}
}
}
Example Usage
Once connected, you can ask Claude:
- "What objects are available in Clarity?"
- "Show me all active projects"
- "How many tasks are in project 5001?"
- "Create a new task called 'Review Requirements' under project 5001"
- "What's the status distribution of all projects?"
- "Show me custom objects"
- "Find fields related to budget"
Architecture
┌─────────────────────────────────────────────────────────┐
│ MCP Client │
│ (Claude, VS Code, etc.) │
└─────────────────────────────────────────────────────────┘
│
│ MCP Protocol
▼
┌─────────────────────────────────────────────────────────┐
│ Clarity PPM MCP Server │
├─────────────────────────────────────────────────────────┤
│ Tools │ Resources │ Services │
│ ───────── │ ────────── │ ──────── │
│ - Discovery │ - Metadata │ - ClarityApiClient │
│ - Records │ - Context │ - MetadataService │
│ - Analytics │ - Links │ - LookupService │
│ - Workflow │ │ - LinkGenerator │
└─────────────────────────────────────────────────────────┘
│
│ REST API
▼
┌─────────────────────────────────────────────────────────┐
│ CA Clarity PPM │
│ (SaaS / On-Premise / Hybrid) │
└─────────────────────────────────────────────────────────┘
Supported Clarity Versions
- Clarity PPM 15.x and above
- Works with SaaS, On-Premise, and Hybrid deployments
Development
# Install dependencies
npm install
# Build
npm run build
# Run in development (with auto-reload)
npm run dev
# Run tests
npm test
License
MIT
Contributing
Contributions welcome! Please read the contributing guidelines first.
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。
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。
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。
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。