ServiceNow MCP Server

A Model Context Protocol (MCP) server that interfaces with ServiceNow, allowing AI agents to access and manipulate ServiceNow data through a secure API. This server enables natural language interactions with ServiceNow, making it easier to search for records, update them, and manage scripts.

Features

Resources

• servicenow://incidents: List recent incidents
• servicenow://incidents/{number}: Get a specific incident by number
• servicenow://users: List users
• servicenow://knowledge: List knowledge articles
• servicenow://tables: List available tables
• servicenow://tables/{table}: Get records from a specific table
• servicenow://schema/{table}: Get the schema for a table

Tools

Basic Tools

• create_incident: Create a new incident
• update_incident: Update an existing incident
• search_records: Search for records using text query
• get_record: Get a specific record by sys_id
• perform_query: Perform a query against ServiceNow
• add_comment: Add a comment to an incident (customer visible)
• add_work_notes: Add work notes to an incident (internal)

Natural Language Tools

• natural_language_search: Search for records using natural language (e.g., “find all incidents about SAP”)
• natural_language_update: Update records using natural language (e.g., “Update incident INC0010001 saying I’m working on it”)
• update_script: Update ServiceNow script files (script includes, business rules, etc.)

Installation

From PyPI

pip install mcp-server-servicenow

From Source

git clone https://github.com/michaelbuckner/servicenow-mcp.git
cd servicenow-mcp
pip install -e .

Usage

Command Line

Run the server using the Python module:

python -m mcp_server_servicenow.cli --url "https://your-instance.service-now.com/" --username "your-username" --password "your-password"

Or use environment variables:

export SERVICENOW_INSTANCE_URL="https://your-instance.service-now.com/"
export SERVICENOW_USERNAME="your-username"
export SERVICENOW_PASSWORD="your-password"
python -m mcp_server_servicenow.cli

Configuration in Cline

To use this MCP server with Cline, add the following to your MCP settings file:

{
  "mcpServers": {
    "servicenow": {
      "command": "/path/to/your/python/executable",
      "args": [
        "-m",
        "mcp_server_servicenow.cli",
        "--url", "https://your-instance.service-now.com/",
        "--username", "your-username",
        "--password", "your-password"
      ],
      "disabled": false,
      "autoApprove": []
    }
  }
}

Note: Make sure to use the full path to the Python executable that has the mcp-server-servicenow package installed.

Natural Language Examples

Searching Records

You can search for records using natural language queries:

find all incidents about email
search for incidents related to network issues
show me all incidents with high priority

Updating Records

You can update records using natural language commands:

Update incident INC0010001 saying I'm working on it
Set incident INC0010002 to in progress
Close incident INC0010003 with resolution: fixed the issue

Managing Scripts

You can update ServiceNow scripts from local files:

Update the ServiceNow script include "HelloWorld" with the contents of hello_world.js
Upload utils.js to ServiceNow as a script include named "UtilityFunctions"
Update @form_validation.js, it's a client script called "FormValidation"

Authentication Methods

The server supports multiple authentication methods:

1. Basic Authentication: Username and password
2. Token Authentication: OAuth token
3. OAuth Authentication: Client ID, Client Secret, Username, and Password

Development

Prerequisites

• Python 3.8+
• ServiceNow instance with API access

Setting Up Development Environment

# Clone the repository
git clone https://github.com/michaelbuckner/servicenow-mcp.git
cd servicenow-mcp

# Create a virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venvScriptsactivate

# Install development dependencies
pip install -e ".[dev]"

Running Tests

pytest

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.