servicenow-mcp

The Most Comprehensive ServiceNow MCP Server

400+ tools · 31+ ServiceNow modules · 5-minute setup · MIT licensed · Works with any AI

servicenow-mcp is the most comprehensive, production-ready MCP server for ServiceNow — and the only one that truly does it all.

Connect Claude, ChatGPT, Gemini, Cursor, GitHub Copilot, or any MCP-compatible AI in under 5 minutes. Then let your AI read, build, deploy, and automate across every ServiceNow module — incidents, changes, scripts, flows, portals, integrations, HRSD, CSM, and more.

Ask in plain English. Deploy business rules from chat. Run ATF suites on demand. Query dev, staging, and prod simultaneously. Automate across multiple customer tenants without switching tabs. Your AI, your instance, your rules.

Any AI. Any instance. Any scale. 100% open-source.

Keywords: ServiceNow MCP server · Model Context Protocol · ServiceNow AI · ITSM automation · ServiceNow Claude · ServiceNow ChatGPT · ServiceNow Cursor · ServiceNow Copilot · ServiceNow LLM · ServiceNow agent · MCP tools · ServiceNow API · agentic AI · ServiceNow developer tools

Who Is This For?

Beginners

Zero ServiceNow API knowledge required.

Connect Claude Desktop or Cursor to your free PDI in 5 minutes. Ask questions in plain English, browse incidents, search KB articles, place catalog orders, monitor SLAs — all from your AI chat window. No code. No Postman. No documentation diving. Just ask.

Start here → 5-Minute Quickstart

Developers

10x faster with AI as your development partner.

Write business rules, deploy client scripts, manage UI Policies and ACLs, create Service Portal widgets, configure REST Messages, manage Transform Maps, and update changesets — all in plain English. Full TypeScript types, ATF integration, and role-based packages built in.

Explore → Platform Developer Package

Architects, Admins & MSPs

Autonomous workflows. Multi-instance. Multi-customer.

Trigger Agentic Playbooks, orchestrate multi-step ITSM/HRSD/CSM processes, compare environments side by side, manage dozens of customer tenants in one session, and run full data quality audits — at AI speed, across your entire ServiceNow estate.

Deep dive → Now Assist & Agentic Guide

Why servicenow-mcp

Fully Autonomous AI Operations

Your AI doesn't just answer questions — it acts. Create incidents, write and deploy scripts, trigger flows, fire events, upload attachments, manage changesets, and run full ATF suites — end-to-end, without manual steps. Native Now Assist Agentic Playbook support for next-generation ServiceNow AI automation.

Works With Every AI, Out of the Box

Claude, ChatGPT, Gemini, Grok, Cursor, Windsurf, GitHub Copilot, Amazon Q, JetBrains, Continue.dev, Cline, Zed, Google AI Studio, Ollama — all supported out of the box. Any MCP-compatible client. Any custom Python or TypeScript agent. One server, every AI platform, zero lock-in.

Unmatched Platform Coverage

400+ production-ready tools across every ServiceNow domain — ITSM, ITOM, HRSD, CSM, SecOps, GRC, Agile, ATF, Flow Designer, Scripting, Now Assist, Service Portal, Integration Hub, Performance Analytics, System Properties, Update Sets, Virtual Agent, ITAM, DevOps, Machine Learning, Workspace/UIB, Mobile, and Deployment. Nothing else comes close.

Role-Based Tool Intelligence

Fourteen pre-built persona packages — service desk, platform developer, portal developer, integration engineer, ITOM engineer, AI developer, ITAM analyst, DevOps engineer, and more. Each exposes exactly the right tools for that role. Reduce noise, enforce least-privilege, and configure once per team.

Safe by Default, Powerful When Needed

A five-tier permission model keeps your instance protected. Read is always on. Write, CMDB, Scripting, Now Assist, and ATF capabilities each require an explicit opt-in flag. No AI can accidentally modify your production data. Scale permissions as your confidence grows — without touching code.

True Multi-Instance & Multi-Customer

Connect to unlimited ServiceNow instances from one session — dev, staging, prod, and multiple customer tenants simultaneously. Pass instance: "acme_prod" on any tool call, or switch_instance globally. MSPs, consultants, and enterprise teams can compare, query, and automate across every environment at once. No other ServiceNow MCP server does this.

Quick Links

Module Coverage

Domain modules covering the full ServiceNow platform:

Authentication

Two authentication methods are supported:

For OAuth setup in ServiceNow, see docs/SERVICENOW_OAUTH_SETUP.md.

Permission System

A five-tier permission model keeps your instance safe by default:

Role-Based Tool Packages

Set MCP_TOOL_PACKAGE to expose only the tools relevant to each persona:

Getting Started

Option A — Interactive Setup Wizard (Recommended)

# Install globally (Node.js 20+ required)
npm install -g @aartiq/servicenow-mcp

# Run the wizard — detects your AI clients and writes config automatically
npx @aartiq/servicenow-mcp setup

The wizard will:

1. Ask for your ServiceNow instance URL + credentials

2. Test the connection

3. Let you pick a tool package and permission level

4. Detect Claude Desktop, Cursor, VS Code, Windsurf, Continue.dev, Claude Code on your machine

5. Write the config directly — no copy-paste, no manual JSON editing

# Add a second instance later
servicenow-mcp setup --add

# Manage instances
servicenow-mcp instances list

Option B — Manual Setup

git clone https://github.com/aartiq/servicenow-mcp.git && cd servicenow-mcp
npm install && npm run build
cp .env.example .env   # fill in your ServiceNow credentials

Then point your AI client at dist/server.js — see Supported AI Clients below.

No ServiceNow instance? Get a free Personal Developer Instance at developer.servicenow.com — ready in minutes.

Full installation guide → docs/INSTALLATION.md

Client Setup Guides

Step-by-step setup for every major AI client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, GitHub Copilot, Continue.dev, Cline, JetBrains, Amazon Q, Google AI Studio, ChatGPT, Grok, Ollama, and more.

Full guide → docs/CLIENT_SETUP.md

For quick setup snippets, see the Supported AI Clients section below.

Example Interactions

Once connected, ask your AI assistant in plain language:

ITSM & Change Management:

Show me all open P1 incidents assigned to the Network Operations group.

Create a normal change request for deploying the new API gateway — implementation planned for Saturday midnight.

What CMDB CIs does the ERP application depend on?

Scripting & Development:

List all client scripts on the incident table and show me the ones that fire on form load.

Create a UI action button "Escalate to L3" on the incident form that assigns the ticket to the L3-Support group.

Show me all ACL rules for the change_request table that restrict the "delete" operation.

Service Portal & UI Builder:

List all widgets in the Service Portal that contain "catalog" in their name.

Get the full source code of the "Stock Ticker" widget so I can update its server script.

Create a new portal widget called "My Approvals Widget" with a simple Angular template that lists pending approvals.

Integrations & Events:

List all REST Message definitions that connect to external APIs.

Show me all transform maps that target the incident table.

Fire the custom event "myapp.ticket.escalated" on incident INC0012345.

For 120+ real-world examples with inputs, outputs, and advanced workflows, see EXAMPLES.md.

Slash Commands & @ Mentions

Once connected, type / in Claude Desktop or Cursor to see built-in ServiceNow shortcuts:

Type @ to pull live ServiceNow data into your AI context:

Add your own commands in servicenow-mcp.commands.json:

[
  {
    "name": "my-p1-runbook",
    "description": "P1 runbook for my team",
    "template": "List all P1 incidents in the Network category. For each: number, description, assignee, time open. Flag SLA breaches."
  }
]

Advanced Configuration

Supported AI Clients

Any MCP-compatible AI works. servicenow-mcp has been tested with every major AI assistant, editor, and agent framework. Pick yours and follow the 3-step setup below.

AI Assistants & Chat

1. Install Claude Desktop from claude.ai/download

2. Edit config:

   • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

   • Windows: %APPDATA%\Claude\claude_desktop_config.json

3. Add this block — single instance (replace path and credentials):

{
  "mcpServers": {
    "servicenow-mcp": {
      "command": "node",
      "args": ["/absolute/path/to/servicenow-mcp/dist/server.js"],
      "env": {
        "SERVICENOW_INSTANCE_URL": "https://yourinstance.service-now.com",
        "SERVICENOW_AUTH_METHOD": "basic",
        "SERVICENOW_BASIC_USERNAME": "admin",
        "SERVICENOW_BASIC_PASSWORD": "your_password",
        "WRITE_ENABLED": "false"
      }
    }
  }
}

Or use multi-instance (dev + staging + prod, or multiple customer tenants):

{
  "mcpServers": {
    "servicenow-mcp": {
      "command": "node",
      "args": ["/absolute/path/to/servicenow-mcp/dist/server.js"],
      "env": {
        "SN_INSTANCES_CONFIG": "/absolute/path/to/instances.json"
      }
    }
  }
}

Copy instances.example.json → instances.json, fill in your instances, then ask:

"List instances" → "Switch to prod" → "Show me all P1 incidents" "Get open changes from customer_acme" (uses instance parameter per-call)

4. Restart Claude Desktop. The hammer icon confirms connection.

Full guide → clients/claude-desktop/SETUP.md | docs/MULTI_INSTANCE.md

OpenAI supports MCP via the Responses API (mcp tool type) in the latest SDK (v1.50+):

from openai import OpenAI
import os, subprocess

# Start servicenow-mcp as a subprocess MCP server
proc = subprocess.Popen(
    ["node", "/path/to/servicenow-mcp/dist/server.js"],
    stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE,
    env={**os.environ,
         "SERVICENOW_INSTANCE_URL": "https://yourinstance.service-now.com",
         "SERVICENOW_AUTH_METHOD": "basic",
         "SERVICENOW_BASIC_USERNAME": "admin",
         "SERVICENOW_BASIC_PASSWORD": "your_password"}
)

client = OpenAI()
response = client.responses.create(
    model="gpt-4o",
    tools=[{"type": "mcp", "server_label": "servicenow-mcp"}],
    input="Show me all open P1 incidents"
)

Full guide → docs/CLIENT_SETUP.md

1. Install servicenow-mcp: npm install -g @aartiq/servicenow-mcp

2. Use the Python client in clients/gemini/:

pip install google-generativeai
python clients/gemini/servicenow_gemini_client.py

Full guide → clients/gemini/SETUP.md

AI Code Editors

1. Open Cursor → Settings → MCP

2. Add server config:

{
  "mcpServers": {
    "servicenow-mcp": {
      "command": "node",
      "args": ["/absolute/path/to/servicenow-mcp/dist/server.js"],
      "env": {
        "SERVICENOW_INSTANCE_URL": "https://yourinstance.service-now.com",
        "SERVICENOW_AUTH_METHOD": "basic",
        "SERVICENOW_BASIC_USERNAME": "admin",
        "SERVICENOW_BASIC_PASSWORD": "your_password",
        "WRITE_ENABLED": "true",
        "SCRIPTING_ENABLED": "true"
      }
    }
  }
}

3. Restart Cursor. Ask in Chat: "List all open P1 incidents"

Multi-instance: Replace the env block with "SN_INSTANCES_CONFIG": "/path/to/instances.json" to connect to multiple tenants.

Full guide → clients/cursor/SETUP.md

1. Open Windsurf → Cascade → Configure MCP

2. Add the same JSON block as Cursor above

3. Reload Windsurf window

Full guide → docs/CLIENT_SETUP.md

1. Open Zed → ~/.config/zed/settings.json

2. Add under "context_servers":

{
  "context_servers": {
    "servicenow-mcp": {
      "command": { "path": "node", "args": ["/path/to/servicenow-mcp/dist/server.js"] },
      "settings": {
        "SERVICENOW_INSTANCE_URL": "https://yourinstance.service-now.com",
        "SERVICENOW_AUTH_METHOD": "basic",
        "SERVICENOW_BASIC_USERNAME": "admin",
        "SERVICENOW_BASIC_PASSWORD": "your_password"
      }
    }
  }
}

Full guide → docs/CLIENT_SETUP.md

IDE Extensions

VS Code 1.99 and later includes built-in MCP support — no extension or subscription required.

1. Install VS Code 1.99+

2. Create .vscode/mcp.json in your workspace (or edit User settings):

{
  "servers": {
    "servicenow-mcp": {
      "type": "stdio",
      "command": "node",
      "args": ["/absolute/path/to/servicenow-mcp/dist/server.js"],
      "env": {
        "SERVICENOW_INSTANCE_URL": "https://yourinstance.service-now.com",
        "SERVICENOW_AUTH_METHOD": "basic",
        "SERVICENOW_BASIC_USERNAME": "admin",
        "SERVICENOW_BASIC_PASSWORD": "your_password",
        "WRITE_ENABLED": "true",
        "SCRIPTING_ENABLED": "true"
      }
    }
  }
}

3. Open the Command Palette (Cmd/Ctrl+Shift+P) → MCP: List Servers to verify the connection

4. Open Copilot Chat (or any AI assistant in VS Code) and use @servicenow-mcp or just ask naturally

Tip: Add .vscode/mcp.json to .gitignore if it contains credentials, or use environment variables from a .env file.

Full guide → clients/vscode/SETUP.md

1. Install VS Code + GitHub Copilot extension

2. Create .vscode/mcp.json in your project:

{
  "servers": {
    "servicenow-mcp": {
      "type": "stdio",
      "command": "node",
      "args": ["${workspaceFolder}/../../servicenow-mcp/dist/server.js"],
      "env": {
        "SERVICENOW_INSTANCE_URL": "https://yourinstance.service-now.com",
        "SERVICENOW_AUTH_METHOD": "basic",
        "SERVICENOW_BASIC_USERNAME": "admin",
        "SERVICENOW_BASIC_PASSWORD": "your_password"
      }
    }
  }
}

3. Open Copilot Chat → Agent mode → @servicenow-mcp

Full guide → clients/vscode/SETUP.md

1. Install Continue from VS Code Marketplace

2. Edit ~/.continue/config.json:

{
  "mcpServers": [
    {
      "name": "servicenow-mcp",
      "command": "node",
      "args": ["/path/to/servicenow-mcp/dist/server.js"],
      "env": {
        "SERVICENOW_INSTANCE_URL": "https://yourinstance.service-now.com",
        "SERVICENOW_AUTH_METHOD": "basic",
        "SERVICENOW_BASIC_USERNAME": "admin",
        "SERVICENOW_BASIC_PASSWORD": "your_password"
      }
    }
  ]
}

Full guide → docs/CLIENT_SETUP.md

1. Install Cline from VS Code Marketplace

2. Open Cline → MCP Servers → Add Server

3. Enter the path to servicenow-mcp/dist/server.js and your environment variables

Full guide → docs/CLIENT_SETUP.md

1. Install JetBrains AI Assistant plugin

2. Go to Settings → Tools → AI Assistant → MCP Servers

3. Add a new server with the path to servicenow-mcp/dist/server.js

4. Set environment variables in the server configuration dialog

Full guide → docs/CLIENT_SETUP.md

1. Install Amazon Q Developer extension for VS Code or IntelliJ

2. Configure MCP via ~/.aws/amazonq/mcp.json:

{
  "mcpServers": {
    "servicenow-mcp": {
      "command": "node",
      "args": ["/path/to/servicenow-mcp/dist/server.js"],
      "env": {
        "SERVICENOW_INSTANCE_URL": "https://yourinstance.service-now.com",
        "SERVICENOW_AUTH_METHOD": "basic",
        "SERVICENOW_BASIC_USERNAME": "admin",
        "SERVICENOW_BASIC_PASSWORD": "your_password"
      }
    }
  }
}

Full guide → docs/CLIENT_SETUP.md

CLI & Terminal Agents

# Install Claude Code
npm install -g @anthropic-ai/claude-code

# Register servicenow-mcp as an MCP server
claude mcp add servicenow-mcp node /absolute/path/to/servicenow-mcp/dist/server.js \
  --env SERVICENOW_INSTANCE_URL=https://yourinstance.service-now.com \
  --env SERVICENOW_AUTH_METHOD=basic \
  --env SERVICENOW_BASIC_USERNAME=admin \
  --env SERVICENOW_BASIC_PASSWORD=your_password

# Verify
claude mcp list

# Use it
claude "Show me all unresolved P1 incidents"

Full guide → clients/claude-code/SETUP.md

1. Install Ollama and pull a model: ollama pull llama3

2. Use an MCP-compatible client (e.g. Cline or Continue) configured to use Ollama as the model

3. Point the MCP server at servicenow-mcp/dist/server.js

Full guide → docs/CLIENT_SETUP.md

Quick Reference

What's New in v1.0

Initial public release of servicenow-mcp — 400+ ServiceNow MCP tools, full CLI, multi-instance support, and 14 role-based tool packages. See CHANGELOG.md for details.

Documentation

Development

npm install          # install dependencies
npm run build        # compile TypeScript → dist/
npm test             # run unit tests
npm run dev          # watch mode (hot reload)
npm run type-check   # TypeScript type check only
npm run lint         # lint

Project Structure

src/
  server.ts              — MCP server entry point (stdio)
  servicenow/
    client.ts            — ServiceNow REST API client (Basic / OAuth / per-user)
    instances.ts         — Multi-instance manager
    types.ts             — TypeScript type definitions + AuthMode
  tools/
    index.ts             — Tool router & role-based package system
    core.ts, incident.ts, change.ts, problem.ts, task.ts
    knowledge.ts, catalog.ts, user.ts, reporting.ts, atf.ts
    now-assist.ts, script.ts, agile.ts, hrsd.ts, csm.ts
    security.ts, flow.ts, portal.ts, integration.ts, notification.ts
    performance.ts, sys-properties.ts, updateset.ts, va.ts, itam.ts, devops.ts
  prompts/
    index.ts             — MCP prompts registry (/ slash commands)
    itsm.ts              — 11 built-in slash commands
    user-prompts.ts      — Custom commands from servicenow-mcp.commands.json
  resources/
    index.ts             — MCP resources (@ mentions)
  cli/
    index.ts             — CLI entry point (commander.js)
    setup.ts             — Interactive setup wizard
    detect-clients.ts    — Auto-detect installed AI clients
    config-store.ts      — ~/.config/servicenow-mcp/instances.json
    auth.ts              — servicenow-mcp auth login/logout/whoami
    writers/index.ts     — Write configs to AI client config files
  utils/
    permissions.ts       — Five-tier permission gate functions
    errors.ts            — Typed error classes
    logging.ts           — Structured logger
tests/
  tools/                 — Unit tests
docs/                    — Reference documentation
clients/
  claude-desktop/        — Claude Desktop setup guide
  cursor/                — Cursor setup guide
  vscode/                — VS Code setup guide
  claude-code/           — Claude Code setup guide
  codex/                 — OpenAI Codex Python client
  gemini/                — Google Gemini Python client
smithery.yaml            — Smithery registry config

Contributing

Contributions are welcome. Please read CONTRIBUTING.md before opening a pull request.

• Bug reports and feature requests: open an issue

• New tool domains, additional tests, or documentation improvements are especially appreciated

• All PRs require npm test to pass

Security

If you discover a security vulnerability, please follow the responsible disclosure process in SECURITY.md. Do not open a public issue.

Frequently Asked Questions

Do I need to know the ServiceNow API to use this? No. For beginners, you just connect your AI and ask questions in plain English. The server handles all API calls automatically.

Which ServiceNow versions are supported? All actively supported ServiceNow releases. The server targets the latest available APIs and has been tested on the three most recent releases.

Can I use this on a free Personal Developer Instance (PDI)? Yes. Get a free PDI at developer.servicenow.com and connect in 5 minutes.

Is it safe to use on production? Yes. The permission system is read-only by default. Write, scripting, and Now Assist capabilities must each be explicitly enabled with environment variables. Use role packages to limit the tool surface.

Does it support multi-instance / multiple customers? Yes. Configure any number of instances (prod, staging, dev, or multiple customer tenants) via instances.json or environment variables. Use list_instances, switch_instance, and get_current_instance tools to manage them, or pass instance: "name" to any individual tool call. See docs/MULTI_INSTANCE.md.

Is it free? Completely free and open-source under the MIT license.

License

MIT — free for personal and commercial use.

The only ServiceNow MCP server you'll ever need.

400+ tools. 31+ modules. Every AI platform. True multi-instance. Open-source forever.

servicenow-mcp • ServiceNow MCP Server • ServiceNow AI Agent • ServiceNow Claude Integration • ServiceNow ChatGPT • ServiceNow Cursor • ServiceNow Gemini • ServiceNow Automation • ServiceNow Developer Tools • ServiceNow Multi-Instance • ServiceNow MSP

If servicenow-mcp saves you time, please ⭐ star the repository — it helps others find the project.