ITSM Integration Platform
MCP FOR ITSM TOOL INTEGRATION
madosh
README
MCP ITSM Integration
A Model Context Protocol (MCP) implementation for IT Service Management (ITSM) tools, designed to work with Smithery.
Overview
This project provides a unified interface for LLMs to interact with multiple ITSM systems (ServiceNow, Jira, Zendesk, Ivanti Neurons for ITSM, and Cherwell) using the Model Context Protocol (MCP). Instead of requiring LLMs to learn different APIs for each ITSM system, this integration provides a standardized set of tools that work across all systems.
MCP Server Information
This is an MCP-compliant server that implements the Model Context Protocol specification. It provides a standardized interface for Large Language Models to interact with multiple ITSM systems through a unified set of tools.
MCP Compatibility
- Protocol Version: MCP 1.0
- Tool Format: JSON Schema compliant
- Runtime: Node.js
- Transport: HTTP and stdio
- Authentication: API key
MCP Server Usage
The server can be used directly with any MCP-compatible client, including:
- MCP Inspector CLI tool
- Claude via MCP integration
- Any LLM with MCP support
To inspect the server locally:
npx @modelcontextprotocol/inspector node index.js
Features
- Unified Interface: Consistent tool definitions across all ITSM systems
- Intelligent Routing: Automatically routes requests to the appropriate ITSM system
- Context Management: Maintains context across interactions
- MCP Compliant: Follows the Model Context Protocol specification
- Smithery Integration: Designed to work seamlessly with Smithery
Prerequisites
- Node.js (v14 or higher)
- Smithery CLI
- Access to ITSM systems (ServiceNow, Jira, Zendesk, Ivanti Neurons for ITSM, Cherwell)
Installation
-
Clone the repository:
git clone https://github.com/yourusername/mcp-itsm.git cd mcp-itsm
-
Install dependencies:
npm install
-
Configure your ITSM credentials (see Configuration section)
-
Deploy to Smithery:
smithery deploy
Configuration
ITSM Credentials
Create a .env
file with your ITSM credentials:
# ServiceNow
SERVICENOW_INSTANCE=your-instance
SERVICENOW_USERNAME=your-username
SERVICENOW_PASSWORD=your-password
# Jira
JIRA_URL=https://your-instance.atlassian.net
JIRA_USERNAME=your-username
JIRA_API_TOKEN=your-api-token
# Zendesk
ZENDESK_URL=https://your-instance.zendesk.com
ZENDESK_EMAIL=your-email
ZENDESK_API_TOKEN=your-api-token
# Ivanti Neurons for ITSM
IVANTI_URL=https://your-instance.ivanti.com
IVANTI_CLIENT_ID=your-client-id
IVANTI_CLIENT_SECRET=your-client-secret
IVANTI_TENANT_ID=your-tenant-id
# Cherwell
CHERWELL_URL=https://your-instance.cherwell.com
CHERWELL_CLIENT_ID=your-client-id
CHERWELL_AUTH_MODE=internal
CHERWELL_USERNAME=your-username
CHERWELL_PASSWORD=your-password
Smithery Configuration
The smithery.yaml
file configures how your tools are deployed to Smithery:
name: mcp-itsm
description: MCP ITSM Tools for ticket management across multiple systems
version: 1.0.0
tools: ./tools.json
command: node index.js
Available Tools
This integration provides the following tools:
- create_ticket: Create a new ticket in any ITSM system
- get_ticket: Retrieve ticket details
- update_ticket: Update an existing ticket
- list_tickets: List tickets with filtering options
- assign_ticket: Assign a ticket to a user
- add_comment: Add a comment to a ticket
- search_knowledge_base: Search the knowledge base for relevant articles
See tools.json
for the complete tool definitions.
Usage
Once deployed to Smithery, LLMs can use these tools to interact with your ITSM systems. Here's an example of how an LLM might create a ticket:
User: "I need to report a bug in our accounting software"
LLM: (Makes a tool call)
{
"type": "tool_call",
"data": {
"name": "create_ticket",
"parameters": {
"title": "Bug in accounting software",
"description": "User reported an issue with the accounting software",
"priority": "medium",
"system": "jira"
}
}
}
Response:
{
"type": "tool_response",
"data": {
"name": "create_ticket",
"content": {
"id": "ACCT-123",
"status": "open",
"url": "https://your-instance.atlassian.net/browse/ACCT-123"
}
}
}
Debugging
This project includes several debugging tools:
debug_smithery_mcp.bat
: Diagnoses MCP-specific issues with Smitheryforce_redeploy_smithery.bat
: Forces redeployment with MCP configurationtest_tools.js
: Tests MCP tool calls locally
Documentation
- MCP Integration: Details of the Model Context Protocol implementation
- MCP Quick Reference: Quick reference guide for MCP concepts
- ITSM Systems Reference: Detailed information about each supported ITSM system
- OpenAI to MCP Conversion: Guide for converting from OpenAI function calling to MCP
Diagrams
- MCP ITSM Architecture: Overall architecture of the integration
- System Fragmentation: The challenge of ITSM system fragmentation
- LLM Reasoning: How LLMs select the appropriate ITSM system
- Benefits Comparison: Comparison of traditional vs. MCP approach
- Smithery Integration: How MCP integrates with Smithery
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Resources
- Model Context Protocol
- Smithery Documentation
- OpenAI Function Calling <a href="https://glama.ai/mcp/servers/hud80wep9g"> <img width="380" height="200" src="https://glama.ai/mcp/servers/hud80wep9g/badge" /> </a>
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
AIO-MCP Server
🚀 All-in-one MCP server with AI search, RAG, and multi-service integrations (GitLab/Jira/Confluence/YouTube) for AI-enhanced development workflows. Folk from
React MCP
react-mcp integrates with Claude Desktop, enabling the creation and modification of React apps based on user prompts
Atlassian Integration
Model Context Protocol (MCP) server for Atlassian Cloud products (Confluence and Jira). This integration is designed specifically for Atlassian Cloud instances and does not support Atlassian Server or Data Center deployments.

Any OpenAI Compatible API Integrations
Integrate Claude with Any OpenAI SDK Compatible Chat Completion API - OpenAI, Perplexity, Groq, xAI, PyroPrompts and more.
MySQL Server
Allows AI assistants to list tables, read data, and execute SQL queries through a controlled interface, making database exploration and analysis safer and more structured.
Browser Use (used by Deploya.dev)
AI-driven browser automation server that implements the Model Context Protocol to enable natural language control of web browsers for tasks like navigation, form filling, and visual interaction.
Aindreyway Codex Keeper
Serves as a guardian of development knowledge, providing AI assistants with curated access to latest documentation and best practices.