ServiceNow MCP Server
Enables users to search and retrieve ServiceNow tickets, knowledge base articles, and service catalog items through the Model Context Protocol.
README
ServiceNow MCP Server on Azure Container Apps
This project hosts a Model Context Protocol (MCP) server that exposes ServiceNow ticket, knowledge base, and service catalog data over Streamable HTTP.
Tools exposed
| MCP tool | Purpose |
|---|---|
servicenow_search_tickets |
Search incident, problem, change_request, sc_request, or sc_task records. |
servicenow_get_ticket |
Read one ticket by sys_id. |
servicenow_search_knowledge |
Search published kb_knowledge articles. |
servicenow_list_catalog_items |
Search active sc_cat_item catalog items. |
servicenow_get_catalog_item |
Read one catalog item by sys_id. |
Local setup
-
Install dependencies:
npm install -
Copy
.env.exampleto.envand set your ServiceNow instance and credentials:Copy-Item .env.example .env -
Start the server:
npm run dev -
The MCP endpoint is:
http://localhost:3000/mcp
ServiceNow permissions
Use a dedicated ServiceNow integration account or OAuth app with least-privilege read access to:
incidentproblemchange_requestsc_requestsc_taskkb_knowledgesc_cat_item
For production, prefer OAuth bearer tokens or a ServiceNow OAuth client flow over basic auth.
Deploy to Azure Container Apps
Set these variables first:
$RESOURCE_GROUP = "rg-servicenow-mcp"
$LOCATION = "centralindia"
$ACR_NAME = "acrsnowmcp$((Get-Random -Maximum 99999))"
$ENV_NAME = "cae-servicenow-mcp"
$APP_NAME = "servicenow-mcp"
$IMAGE_NAME = "servicenow-mcp-server:0.1.0"
$SERVICENOW_URL = "https://your-instance.service-now.com"
$SERVICENOW_USERNAME = "your-integration-user"
$SERVICENOW_PASSWORD = "your-password"
Create Azure resources and build the image:
az group create --name $RESOURCE_GROUP --location $LOCATION
az acr create --resource-group $RESOURCE_GROUP --name $ACR_NAME --sku Basic --admin-enabled true
az acr build --registry $ACR_NAME --image $IMAGE_NAME .
az containerapp env create --name $ENV_NAME --resource-group $RESOURCE_GROUP --location $LOCATION
Deploy the container app:
$ACR_LOGIN_SERVER = az acr show --name $ACR_NAME --query loginServer -o tsv
$ACR_USERNAME = az acr credential show --name $ACR_NAME --query username -o tsv
$ACR_PASSWORD = az acr credential show --name $ACR_NAME --query "passwords[0].value" -o tsv
az containerapp create `
--name $APP_NAME `
--resource-group $RESOURCE_GROUP `
--environment $ENV_NAME `
--image "$ACR_LOGIN_SERVER/$IMAGE_NAME" `
--target-port 3000 `
--ingress external `
--registry-server $ACR_LOGIN_SERVER `
--registry-username $ACR_USERNAME `
--registry-password $ACR_PASSWORD `
--secrets `
servicenow-url=$SERVICENOW_URL `
servicenow-username=$SERVICENOW_USERNAME `
servicenow-password=$SERVICENOW_PASSWORD `
--env-vars `
SERVICENOW_INSTANCE_URL=secretref:servicenow-url `
SERVICENOW_USERNAME=secretref:servicenow-username `
SERVICENOW_PASSWORD=secretref:servicenow-password
Get the public MCP URL:
$FQDN = az containerapp show --name $APP_NAME --resource-group $RESOURCE_GROUP --query properties.configuration.ingress.fqdn -o tsv
"https://$FQDN/mcp"
Health check:
curl.exe "https://$FQDN/healthz"
Use OAuth token instead of basic auth
Replace the username/password secret and environment variable lines with:
--secrets servicenow-url=$SERVICENOW_URL servicenow-oauth-token=$SERVICENOW_OAUTH_TOKEN `
--env-vars SERVICENOW_INSTANCE_URL=secretref:servicenow-url SERVICENOW_OAUTH_TOKEN=secretref:servicenow-oauth-token
Production hardening
- Put Azure API Management or an authenticated ingress in front of the MCP endpoint.
- Restrict Container Apps ingress to your corporate network where possible.
- Use Azure Key Vault secret references for ServiceNow credentials.
- Create a dedicated ServiceNow integration user with read-only ACLs.
- Add log analytics alerts for repeated ServiceNow API failures.
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.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.