TrueNAS Middleware MCP Server
Provides optimized documentation and API patterns from the TrueNAS middleware repository to help AI assistants understand its codebase structure without context overload. It automatically processes CLAUDE.md files to expose categorized resources including plugin guides, API models, and testing patterns.
README
TrueNAS Middleware MCP Server
This MCP (Model Context Protocol) server provides optimized documentation resources from the TrueNAS middleware repository to Code Claude, helping it understand the codebase structure and APIs without context overload.
Quick Start
- For Code Claude Integration: See INTEGRATION_GUIDE.md
- For Usage in Code Claude: See QUICK_REFERENCE.md
- For Adding Documentation: See DOCUMENTATION_GUIDE.md
- For Plugin Doc Template: See PLUGIN_DOCUMENTATION_TEMPLATE.md
- For Development Plans: See ACTION_PLAN.md
Features
- Automatically discovers and processes all CLAUDE.md files in the middleware repository
- Organizes documentation into logical categories (Overview, Plugins, API, Testing, Subsystems)
- Provides concise, focused resources to avoid context overload
- Implements intelligent content summarization
Setup Options
Option 1: Native Python (Recommended)
- Create and activate the virtual environment:
python3.11 -m venv venv_tn_mcp
source venv_tn_mcp/bin/activate # On Windows: venv_tn_mcp\Scripts\activate
- Install dependencies:
pip install -r requirements.txt
- Run the server:
./run_server.sh # Or: python truenas_mcp_server.py
Option 2: Docker Container
- Build the Docker image:
docker-compose build
- Run the server:
docker-compose run --rm truenas-mcp
Available Resources
The server provides the following types of resources:
Overview Resources
truenas://overview- High-level middleware architecturetruenas://development/guidelines- Development best practices
Plugin Resources
truenas://plugins/service-types- Guide to service base classestruenas://plugins/patterns- Common plugin patternstruenas://plugins/categories- Categorized plugin listtruenas://plugins/{plugin_name}- Specific plugin documentation
API Resources
truenas://api/versioning- API versioning guidetruenas://api/models- Pydantic model patterns
Testing Resources
truenas://testing/overview- Testing guidetruenas://testing/patterns- Common testing patterns
Subsystem Resources
truenas://subsystems/{name}- Documentation for specific subsystems
Integration with Code Claude
See INTEGRATION_GUIDE.md for detailed setup instructions.
Quick Config (add to claude_desktop_config.json):
{
"mcpServers": {
"truenas-docs": {
"command": "/path/to/venv_tn_mcp/bin/python",
"args": ["/path/to/tn_mcp/truenas_mcp_server.py"]
}
}
}
How It Works
- The server scans the middleware repository for all CLAUDE.md files
- Each file is processed and categorized based on its location
- Content is intelligently summarized to reduce context size
- Resources are exposed via MCP protocol for Code Claude to query
Optimization Strategy
To avoid context overload, the server:
- Extracts key sections from documentation
- Limits code examples to essential ones
- Focuses on API signatures and patterns rather than full implementations
- Groups related information into logical resources
Running Tests
Tests are run using Docker to ensure a consistent environment.
Run All Tests
docker-compose run --rm truenas-mcp-test
Run Specific Test File
docker-compose run --rm truenas-mcp-test pytest tests/test_truenas_mcp_tools_server.py -v
Run with Coverage
docker-compose run --rm truenas-mcp-test pytest --cov=. --cov-report=html
Running Middleware Tests
The server includes a tool for running TrueNAS middleware tests. Use the run_middleware_tests.sh script:
# Run all middleware tests
./run_middleware_tests.sh
# Run a specific test file
./run_middleware_tests.sh . test_construct_schema.py
# Clean up test container
./run_middleware_tests.sh /path/to/middleware --cleanup
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。