OpenL MCP Server

OpenL MCP Server

Enables AI assistants to interact with OpenL Studio's business rules management system, allowing repository, project, rule, and deployment management via natural language.

Category
访问服务器

README

OpenL MCP Server

Model Context Protocol server for OpenL Studio Business Rules Management System.

Built with MCP SDK v1.26+ featuring type-safe validation (Zod) and comprehensive OpenL Studio integration.

Quick Links

npm Distribution

The MCP server is published as an npm package: openl-mcp-server — stdio transport via npx for Claude Desktop / Cursor / VS Code.

For details see README.npm.md.

Quick Start

Run OpenL Studio + MCP with Docker

You only need a local copy of compose.studio.yaml.

docker compose -f compose.studio.yaml up -d

This starts:

  • OpenL Studio image from GHCR: ghcr.io/openl-tablets/webstudio:x
  • MCP image from GHCR: ghcr.io/openl-tablets/openl-mcp:latest
  • OpenL Studio at http://localhost:8080
  • MCP server at http://localhost:3000

For a fast setup, use Method 1 (Docker Compose, recommended) in the Quick Start guide.

Documentation Structure

Getting Started

Setup Guides

  • MCP Connection Guide - Complete guide for connecting Cursor and Claude Desktop to MCP server (Remote and Docker)
  • Docker Setup - Running MCP server in Docker (technical details)

Guides

Development

Reference

OpenL Studio Concepts

OpenL Studio uses dual versioning: Git-based commits (temporal) and dimension properties (business context). Supports multiple table types: Decision Tables (Rules, SimpleRules, SmartRules, Lookups), Spreadsheet Tables, and others (Method, Datatype, Test, etc.).

See prompts/create_rule.md for detailed table type guidance.

Tools

The MCP server provides 25 active tools for managing OpenL Studio repositories, projects, rules, and deployments. All tools are prefixed with openl_ and versioned (v1.0.0+).

Categories:

  • Repository Management (4 tools) - List repositories, branches, features
  • Project Management (12 active + 2 disabled = 14 total) - List, open, save, branch projects, test execution
  • Rules & Tables (5 active + 1 disabled = 6 total) - List, get, update, append, create tables
  • Deployment (4 tools) - List, deploy, redeploy projects

Note: 6 additional tools are temporarily disabled pending implementation fixes.

See Usage Examples for detailed tool usage and Enable Disabled Tools for tool reference.

Prompts

15 expert guidance templates for complex OpenL Studio workflows. Prompts provide contextual assistance, best practices, and step-by-step instructions directly in Claude Desktop or MCP Inspector.

Available prompts: local_projects, create_rule, create_rule_decision_tables, create_rule_spreadsheet, create_test, update_test, run_test, execute_rule, append_table, datatype_vocabulary, dimension_properties, deploy_project, get_project_errors, file_history, project_history.

Usage: Request prompts in Claude Desktop (e.g., "Use the create_rule prompt") or access via MCP Inspector. See prompts/create_rule.md for detailed content.

Configuration

Environment Variables

# Required
OPENL_BASE_URL=<your-base-url>

# Auth Method 1: Basic Auth
OPENL_USERNAME=<your-username>
OPENL_PASSWORD=<your-password>

# Auth Method 2: Personal Access Token
OPENL_PERSONAL_ACCESS_TOKEN=<your-token>

# Optional
OPENL_TIMEOUT=60000

See Authentication Guide for detailed auth setup.

Claude Desktop / Cursor Configuration

See MCP Connection Guide for client-specific configuration instructions.

Key Features

  • Type-Safe: Zod schemas with strict validation and TypeScript inference
  • Multiple Auth Methods: Basic Auth and Personal Access Token (PAT)
  • 4 Response Formats: json, markdown, markdown_concise, markdown_detailed
  • Pagination Support: Metadata for all list operations
  • AI Prompts: 15 expert guidance templates
  • Comprehensive Tests: Full test suite covering core functionality

Development

npm run build          # Build TypeScript
npm test               # Run all tests
npm run lint           # Check code quality
npm run watch          # Dev mode with auto-rebuild

See Contributing Guide for development guidelines and Testing Guide for test suites.

Project Structure

openl-mcp/
├── src/                    # Source code (TypeScript)
├── tests/                  # Jest test suites
├── prompts/                # AI assistant guidance (OpenL-specific)
├── dist/                   # Compiled output
├── docs/                   # Documentation
│   ├── getting-started/    # Quick start and installation
│   ├── setup/              # Client setup guides
│   ├── guides/             # Usage guides and examples
│   ├── development/        # Developer documentation
│   └── reference/          # Reference materials
└── README.md               # This file

Additional Documentation

Resources

License

LGPL-3.0 - GNU Lesser General Public License v3.0 (follows OpenL Studio project license).

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选