servicenow-api
Verified Safeby Knuckles-Team
Overview
Provides a Model Context Protocol (MCP) server to interface with ServiceNow APIs and an Agent2Agent (A2A) agent for orchestrating ServiceNow tasks using LLMs.
Installation
docker run -d -p 8004:8004 -e SERVICENOW_INSTANCE=https://yourinstance.servicenow.com -e SERVICENOW_USERNAME=your_username -e SERVICENOW_PASSWORD=your_password -e TRANSPORT=http -e AUTH_TYPE=none -e EUNOMIA_TYPE=none knucklessg1/servicenow:latestEnvironment Variables
- SERVICENOW_INSTANCE
- SERVICENOW_USERNAME
- SERVICENOW_PASSWORD
- SERVICENOW_CLIENT_ID
- SERVICENOW_CLIENT_SECRET
- ENABLE_DELEGATION
- SERVICENOW_AUDIENCE
- DELEGATED_SCOPES
- OIDC_CONFIG_URL
- OIDC_CLIENT_ID
- OIDC_CLIENT_SECRET
- TOKEN_JWKS_URI
- TOKEN_ISSUER
- TOKEN_AUDIENCE
- TOKEN_ALGORITHM
- TOKEN_SECRET
- TOKEN_PUBLIC_KEY
- REQUIRED_SCOPES
- OPENAPI_FILE
- OPENAPI_USERNAME
- OPENAPI_PASSWORD
- OPENAPI_CLIENT_ID
- OPENAPI_CLIENT_SECRET
- PROVIDER
- MODEL_ID
- BASE_URL
- API_KEY
- MCP_URL
Security Notes
The server implements various robust authentication mechanisms (JWT, OAuth, OIDC) and policy-based authorization (Eunomia), relying on environment variables for sensitive credentials. It uses standard secure practices for API interactions and does not contain `eval`, `exec`, or obvious hardcoded secrets. Default `0.0.0.0` host binding is typical for containers but requires external network security. OIDC token delegation for ServiceNow is a valuable feature but requires careful configuration of `audience` and `scopes`.
Similar Servers
klavis
Creates a universal MCP server that aggregates and manages multiple individual MCP server integrations, allowing AI agents to access a wide range of tools through a single interface for various tasks like email summarization and YouTube video analysis.
mcpo
Exposes Model Context Protocol (MCP) tools as OpenAPI-compatible HTTP servers.
mcp-context-forge
Retrieves web content and files from any URL, converting them into high-quality markdown format with support for various content types and conversion engines.
mcpstore
MCPStore acts as an orchestration layer for managing Microservice Context Protocol (MCP) services and adapting them as tools for AI frameworks like LangChain, AutoGen, and others.