Summary

This project provides a Model Completion Protocol (MCP) server for ServiceNow, enabling AI models like Claude to interact with ServiceNow instances. It serves as a bridge for retrieving data and executing actions via the ServiceNow API, benefiting users who need to integrate AI capabilities with their ServiceNow environment for automation and data access.

How It Works

The server implements the MCP protocol, acting as an intermediary between an AI model and ServiceNow. It leverages ServiceNow's APIs to perform operations such as querying records, creating/updating data, executing scripts, and accessing the Service Catalog. Communication is supported via standard input/output (stdio) or Server-Sent Events (SSE) for flexible integration patterns.

Quick Start & Requirements

• Prerequisites: Python 3.11+, a ServiceNow instance with valid credentials.
• Installation: Clone the repository, create a virtual environment (python -m venv .venv), activate it, and install (pip install -e .).
• Setup: Configure ServiceNow credentials in a .env file (e.g., SERVICENOW_INSTANCE_URL, SERVICENOW_USERNAME, SERVICENOW_PASSWORD, SERVICENOW_AUTH_TYPE).
• Usage: Run via CLI (python -m servicenow_mcp.cli) or start the SSE server (servicenow-mcp-sse).
• Docs: Additional documentation is available in the docs directory.

Highlighted Details

• Authentication: Supports Basic, OAuth, and API Key methods for connecting to ServiceNow.
• Tool Packaging: Enables granular control over exposed tools by defining role-based packages (e.g., service_desk, catalog_builder, platform_developer) configurable via the MCP_TOOL_PACKAGE environment variable.
• Extensive Toolset: Offers a comprehensive suite of tools for Incident Management, Service Catalog operations (creation, optimization), Change Management, Agile Management, Workflow, Script Includes, Changesets, Knowledge Base management, User/Group management, and UI Policies.
• Introspection: Includes a list_tool_packages tool for discovering available toolsets.

Maintenance & Community

Contributions are welcomed via pull requests. No specific details on maintainers, sponsorships, or dedicated community channels (like Discord/Slack) are provided in the README.

Licensing & Compatibility

• License: MIT License.
• Compatibility: The MIT license permits broad use, including commercial applications and linking within closed-source projects.

Limitations & Caveats

The project details troubleshooting steps for common errors, particularly within Change Management tools, suggesting potential areas requiring careful parameter handling or configuration. Tool availability is dependent on the selected package, necessitating explicit configuration for specific use cases.