servicenow
Connects Claude Desktop directly to a ServiceNow instance for incident management, service catalog, workflow tools, and AI-powered smart incidents and KB generation using Gemini.
README
ServiceNow MCP Server with Gemini AI
A powerful Model Context Protocol (MCP) server that connects Claude Desktop directly to your ServiceNow instance. It includes standard tools for record management and AI-powered "Smart" tools using Gemini 1.5 Flash.
🚀 Features
- Incident Management: Create and track incidents.
- Service Catalog: Create Record Producers, Variable Sets, and Variables.
- Workflow Tools: Automate creation of Client Scripts, Business Rules, and SLA Definitions.
- Gemini AI Integration:
smart_incident: Automatically extracts ticket details from messy logs or chat transcripts.smart_kb_generator: Turns rough notes into professional HTML Knowledge Base articles.
🛠️ Setup
1. Prerequisites
- Python 3.12+
- A ServiceNow Developer Instance
- A Google Gemini API Key
2. Installation
Clone the repository and install dependencies:
pip install -e .
3. Environment Configuration
Create a .env file in the root directory:
SERVICENOW_INSTANCE=https://devXXXXX.service-now.com
SERVICENOW_USERNAME=admin
SERVICENOW_PASSWORD=your_password
GEMINI_API_KEY=your_gemini_api_key
🤖 Claude Desktop Configuration
To use this with Claude Desktop, add the following to your claude_desktop_config.json (typically found in %APPDATA%\Claude\):
{
"mcpServers": {
"servicenow": {
"command": "python",
"args": [
"-u",
"C:/Arun/Projects/mcp-server-servicenow/main.py"
]
}
}
}
Note: Ensure the path to main.py is absolute and uses forward slashes /.
📖 Usage Examples
Manual Incident
"Create a high priority incident for the production database being unreachable."
AI-Powered (Smart) Incident
"Based on this chat log [Copy/Paste Log], create a smart incident in ServiceNow."
Knowledge Base Generation
"Turn these bullet points into a KB article for end users: [Your Notes]"
📂 Project Structure
server.py: Core configuration and ServiceNow API client.main.py: Tool implementations and MCP server entry point.
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。