servicenow-mcp

Provides an MCP server that lets an AI client (e.g., Claude) interact with a ServiceNow instance: query records, and perform actions like creating/updating/deleting records, running scripts/workflows, and managing service catalog and related ITSM artifacts via ServiceNow APIs. Supports MCP over stdio and an SSE-based web transport.

Evaluated Mar 30, 2026 (22d ago)
Repo ↗ Automation mcp servicenow automation it-operations agent-tools sse python
⚙ Agent Friendliness
54
/ 100
Can an agent use this?
🔒 Security
65
/ 100
Is it safe for agents?
⚡ Reliability
22
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
70
Documentation
70
Error Messages
0
Auth Simplicity
80
Rate Limits
10

🔒 Security

TLS Enforcement
85
Auth Strength
70
Scope Granularity
40
Dep. Hygiene
55
Secret Handling
70

Transport security likely relies on HTTPS to ServiceNow (README uses instance URL); SSE mode runs a Starlette/Uvicorn app but the README does not specify TLS or access controls for the SSE endpoints. Authentication options include Basic/OAuth/API key, but the README does not discuss scoped permissions for MCP tools. Credentials are passed via environment variables/.env, which is good practice, but the README does not confirm redaction in logs or safe error handling. Dependency hygiene cannot be verified from provided content; versions are only listed in dependencies.

⚡ Reliability

Uptime/SLA
0
Version Stability
30
Breaking Changes
30
Error Recovery
30
AF Security Reliability

Best When

You need an agent to safely perform structured ServiceNow tasks and you can control authentication, tool scope (via MCP_TOOL_PACKAGE), and operational permissions.

Avoid When

You cannot ensure least-privilege credentials or you need strong guarantees around idempotency/audit for write/delete operations.

Use Cases

  • Agent-assisted ITSM operations in ServiceNow (incidents, changes, knowledge, catalog items)
  • Automating catalog item creation/updates and workflow/UI policy management
  • Building operational assistants that can query ServiceNow data and take actions
  • Change/approval orchestration through scripted MCP tool calls
  • Using tool packaging to restrict the set of actions exposed to the model

Not For

  • Untrusted/automated workloads without strict permissioning (tools can create/update/delete ServiceNow data)
  • Environments where outbound network access to ServiceNow must be avoided
  • Use as a general-purpose ServiceNow client without MCP/agent controls and governance

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Basic OAuth API Key
OAuth: Yes Scopes: No

Auth is configured via environment variables (SERVICENOW_AUTH_TYPE) and corresponding credentials in a .env or CLI params. README does not describe fine-grained scopes beyond the ServiceNow-side permissions tied to the credentials.

Pricing

Free tier: No
Requires CC: No

No pricing information in the provided content; this appears to be a self-hosted open-source MCP server.

Agent Metadata

Pagination
unknown
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Write/delete tools are broadly exposed; rely on tool packaging (MCP_TOOL_PACKAGE) and least-privilege credentials to prevent destructive actions.
  • Retries/timeouts are not documented; agent should avoid blindly retrying non-idempotent operations.
  • SSE mode exposes a web server; ensure network exposure and auth controls are handled outside the shown README.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for servicenow-mcp.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered