Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free
6,000+ web scrapers for your AI agent, start free logo6,000+ web scrapers for your AI agent, start free

Apify gives your agent live web data: 6,000+ prebuilt scrapers and actors, MCP-ready. Sign up free with $5 in usage credits.

Try Apify free
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free
Reach 48,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here

Works with

Claude CodeClaude DesktopCursorVS CodeClineCodex CLIOpenClaw+ any MCP client

Install to Claude Code

This server doesn't publish a one-line install command. Follow the setup in the source repository.

Summary

MCP server to interact with ServiceNow instances, enabling ITSM, CMDB, workflow, and knowledge search operations.

README.md

servicenow-mcp

An MCP (Model Context Protocol) server that lets Claude interact with a ServiceNow instance. Exposes ServiceNow functionality as tools Claude can call directly from Claude Desktop or any MCP-compatible client.

Requirements

  • Python 3.10+
  • A ServiceNow instance (developer instance works fine)
  • Claude Desktop or another MCP client

Installation

pip install -r requirements.txt

For RAG-based knowledge search (optional):

pip install chromadb sentence-transformers

Configuration

Set the following environment variables (or copy .env.example to .env):

SERVICENOW_INSTANCE_URL=https://your-instance.service-now.com
SERVICENOW_USERNAME=your-username
SERVICENOW_PASSWORD=your-password

# Optional — enables semantic knowledge search
OPENAI_API_KEY=your-openai-key

Choosing a transport

The server supports two transports:

| Transport | When to use | |---|---| | stdio (default) | Claude Desktop — the standard local setup | | http | Cursor, Cline, LangChain, OpenAI Agents SDK, any web client |

Claude Desktop setup

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "servicenow": {
      "command": "python",
      "args": ["-m", "servicenow_mcp"],
      "env": {
        "SERVICENOW_INSTANCE_URL": "https://your-instance.service-now.com",
        "SERVICENOW_USERNAME": "your-username",
        "SERVICENOW_PASSWORD": "your-password"
      }
    }
  }
}

HTTP transport (Cursor, Cline, LangChain, OpenAI Agents SDK)

Start the server in HTTP mode:

MCP_TRANSPORT=http python -m servicenow_mcp

The MCP endpoint is at http://localhost:8000/mcp.

To require an API key on all requests:

MCP_TRANSPORT=http MCP_API_KEY=your-secret-key python -m servicenow_mcp

Clients must then include Authorization: Bearer your-secret-key in every request.

Cursor / Cline config

{
  "mcpServers": {
    "servicenow": {
      "url": "http://localhost:8000/mcp",
      "headers": {
        "Authorization": "Bearer your-secret-key"
      }
    }
  }
}

Docker + HTTP mode

docker run -p 8000:8000 \
  -e MCP_TRANSPORT=http \
  -e MCP_API_KEY=your-secret-key \
  -e SERVICENOW_INSTANCE_URL=https://your-instance.service-now.com \
  -e SERVICENOW_USERNAME=your-username \
  -e SERVICENOW_PASSWORD=your-password \
  servicenow-mcp

What's included

Tools are grouped into packs by domain:

| Category | Packs | |---|---| | Core development | scripts, dev, background scripts, senior dev | | Data / config | tables, data import/export, update sets, attachments | | ITSM | incidents, changes, problems, requests, approvals | | CMDB / discovery | CMDB, CSDM, discovery, ITAM, ITOM, SAM/HAM | | Workflow | Flow Designer, pipelines, planner | | Integrations | Scripted REST APIs, integration hub | | UI | UI Builder, service catalog, UX | | App development | scoped apps, best practices, naming conventions | | Testing | ATF, troubleshooting | | Knowledge | docs search, knowledge base, RAG search | | Security | governance, impersonation, events |

Running with Docker

If you don't want to deal with Python environments, you can run the server inside Docker instead.

  1. Make sure you have Docker Desktop installed and running.
  1. Copy .env.example to .env and fill in your ServiceNow credentials:
   cp .env.example .env
   # then open .env and set SERVICENOW_INSTANCE_URL, SERVICENOW_USERNAME, SERVICENOW_PASSWORD
  1. Build and start the container:
   docker-compose up --build

The first run will take a minute to download and build everything. After that it's fast.

  1. To stop it:
   docker-compose down

That's it. Logs are saved to a logs/ folder in the project directory.

If you want to use it with Claude Desktop, you still need to run it via python -m servicenow_mcp (the Claude Desktop integration talks over stdin/stdout, not HTTP). Docker is more useful if you're running this as a standalone service or testing it independently.

Running tests

pytest

Contributing

See CONTRIBUTING.md.

License

MIT — see LICENSE.

See related servers & alternatives →

Related MCP servers

Browse all →

Related guides

Hand-picked reading to help you choose and use Vector & Memory servers.