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.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。