ServiceNow MCP Server
A ServiceNow integration server for the Model Context Protocol that enables automated incident management, knowledge base article creation, and other ServiceNow operations through a standardized protocol.
README
🚀 ServiceNow MCP Server
<div align="center"> <img src="images/light.png" alt="MCP Architecture" width="400"/> <p><em>ServiceNow Integration for Model Context Protocol</em></p> </div>
📋 Overview
This repository contains a ServiceNow integration server for the Model Context Protocol (MCP). It enables seamless interaction between ServiceNow instances and AI models through a standardized protocol, allowing for automated incident management, knowledge base article creation, and other ServiceNow operations.
✨ Features
- 🔌 ServiceNow Integration: Direct integration with ServiceNow instances
- 🛠️ Multiple Operations Support:
- Create and manage incidents
- Create knowledge base articles
- Create client scripts
- Create business rules
- Create SLA definitions
- Create record producers
- 🔒 Secure Authentication: Environment-based credentials management
- 🚀 FastAPI-based Server: High-performance async operations
🛠️ Prerequisites
- Python 3.12 or higher
- ServiceNow instance with appropriate API access
- Valid ServiceNow credentials
- Optional: Gemini API key for AI capabilities
- UV icorn for running the server
- FastAPI for building the server
⚙️ Configuration
-
Clone the repository:
git clone https://github.com/your-org/mcp-server-now.git cd mcp-server-now -
Create a
.envfile with your credentials:SERVICENOW_INSTANCE=https://your-instance.service-now.com SERVICENOW_USERNAME=your_username SERVICENOW_PASSWORD=your_password GEMINI_API_KEY=your_api_key # Optional -
Install dependencies:
pip install -e .
🚀 Getting Started
Running the Server
mcp install <file_name>.py
Example Usage
The server provides several tools for ServiceNow operations. Here are some examples:
-
Create an Incident:
create_incident( short_description="Network outage in building B", description="Users reporting connectivity issues", urgency="2", impact="2" ) -
Create a Knowledge Base Article:
create_kb_article( short_description="How to Reset Your Password", article_body="<h1>Password Reset Instructions</h1><p>1. Navigate to the login page</p>", workflow_state="published" )
For more examples, see servicenow-test-examples.md.
🧩 Available Tools
The server provides the following tools:
create_incident: Create new incidentscreate_kb_article: Create knowledge base articlescreate_client_script: Create client-side scriptscreate_business_rule: Create business rulescreate_sla_definition: Create SLA definitionscreate_record_producer: Create record producers with customizable variablescreate_variable_set: Create reusable variable sets for catalog items
Record Producer Details
The create_record_producer tool allows you to create ServiceNow record producers with the following features:
create_record_producer(
name="Report Network Issue",
table_name="incident",
short_description="Use this form to report network connectivity issues",
category_sys_id="optional_category_sys_id",
script="optional_server_side_script",
variables=[
{
"name": "issue_type",
"label": "Type of Issue",
"type": "choice",
"choices": ["Connectivity", "Performance", "Access"],
"mandatory": True
},
{
"name": "affected_users",
"label": "Number of Affected Users",
"type": "integer",
"mandatory": True
}
]
)
Key features:
- Customizable form fields with various types (string, integer, boolean, reference, etc.)
- Server-side scripting support
- Category assignment
- Mandatory field configuration
- Default values and help text
Variable Sets
The create_variable_set tool allows you to create reusable variable sets that can be attached to multiple catalog items:
create_variable_set(
name="Hardware Request Variables",
description="Common variables for hardware requests",
variables=[
{
"name": "device_type",
"label": "Device Type",
"type": "choice",
"choices": ["Laptop", "Desktop", "Tablet", "Phone"],
"mandatory": True
},
{
"name": "justification",
"label": "Justification",
"type": "text",
"mandatory": True,
"help_text": "Please explain why you need this hardware"
}
]
)
Variable sets support:
- Multiple variable types (string, integer, boolean, reference, choice, etc.)
- Custom validation rules
- Help text and descriptions
- Mandatory field configuration
- Default values
- Reference fields to other ServiceNow tables
🔧 Development
Project Structure
mcp-server-now/
├── servicenow.py # Main server implementation
├── servicenow-test-examples.md # Example usage
├── pyproject.toml # Project configuration
├── .env # Environment variables
└── README.md # This file
Adding New Tools
To add new ServiceNow operations:
- Create a new async function in
servicenow.py - Decorate it with
@mcp.tool() - Add proper documentation and error handling
- Test the new functionality
📚 Resources
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
📞 Support
For support, please:
- Open an issue in this repository
- Contact the maintainers
- Check the ServiceNow documentation
👤 Author
<div align="center"> <img src="https://github.com/divyashah0510.png" alt="Divya Shah" width="100"/> <p><strong>Divya Shah</strong></p> <p> AI Engineer | ServiceNow Developer | Open Source Contributor </p> <p> <a href="https://github.com/divyashah0510">GitHub</a> • <a href="https://linkedin.com/in/divya-d-shah">LinkedIn</a> • <a href="https://x.com/Divya_Shah22">Twitter</a> </p> </div>
🎥 Watch Live Demo
Live Demo
<iframe width="560" height="315" src="https://www.youtube.com/embed/FojEOrdFWxo?si=WQZoNOwEe_ktaiJ_" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
<div align="center"> <p>Made with ❤️ by Divya Shah</p> </div>
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。
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。
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。
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。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。
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