Bring Itsm
to Pydantic AI
Learn how to connect ServiceNow to Pydantic AI and start using 10 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for Subscribers
What is the ServiceNow MCP Server?
Connect your ServiceNow instance to any AI agent and manage your entire IT service lifecycle through natural conversation.
What you can do
- Incident Management — Create, update, and resolve incidents. Query open tickets by priority, assignment group, or SLA breach status
- Service Requests — Submit and track service catalog requests, view approval chains, and check fulfillment status
- Change Management — Create change requests, review CAB approvals, and monitor scheduled change windows
- CMDB Queries — Search configuration items, explore CI relationships, and audit asset records across your infrastructure
- Knowledge Base — Search and retrieve knowledge articles to help with incident resolution and self-service
- User Management — Look up user profiles, group memberships, and role assignments across your organization
- Custom Table Queries — Execute SysParm-filtered queries against any ServiceNow table with full dot-walking support
How it works
1. Subscribe to this server
2. Enter your ServiceNow instance URL and credentials
3. Start managing IT operations through Claude, Cursor, or any MCP-compatible client
Your AI agent becomes your ITSM command center — no more navigating complex Fiori dashboards to triage a P1.
Who is this for?
- IT Service Managers — triage incidents and track SLA compliance through simple chat commands
- DevOps Engineers — create change requests and query CMDB relationships without manual data entry
- Help Desk Analysts — resolve tickets faster by searching the knowledge base and updating records via conversation
- IT Directors — get real-time dashboards on incident volume, resolution times, and backlog health
Built-in capabilities (10)
Useful for dashboards and metrics without fetching full records. Get record count from a ServiceNow table
Provide fields as JSON string. Common tables: incident, change_request, sc_request, problem. Create a new record in any ServiceNow table
This action is irreversible. Delete a ServiceNow record
Returns all fields. Get a single ServiceNow record by sys_id
Filter by state, risk, type. Example: risk=high^state=new List change requests
Filter by priority, state, assignment_group, or any field. Example query: priority=1^state=1 (open P1 incidents). List incidents with optional filters
Common tables: cmdb_ci_server, cmdb_ci_appl, cmdb_ci_db_instance, cmdb_ci_network. Example query: name=PROD-WEB-01 Query ServiceNow CMDB configuration items
). Use SysParm encoded query syntax: field=value^field2=value2. Supports dot-walking for related fields. Query any ServiceNow table with SysParm filters
Returns matching articles with KB numbers and descriptions. Search the ServiceNow Knowledge Base
Only specify the fields you want to change. Update an existing ServiceNow record
Why Pydantic AI?
Pydantic AI validates every ServiceNow tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
- —
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
- —
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your ServiceNow integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your ServiceNow connection logic from agent behavior for testable, maintainable code
ServiceNow in Pydantic AI
ServiceNow and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect ServiceNow to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for ServiceNow in Pydantic AI
The ServiceNow MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 10 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
ServiceNow for Pydantic AI
Every tool call from Pydantic AI to the ServiceNow MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I query incidents filtered by priority and assignment group?
Yes. Use the query_table tool with the incident table and SysParm query filters like priority=1^assignment_group=Network. Full dot-walking is supported for related fields.
How do I create a change request through the agent?
Use the create_record tool with the change_request table. Provide key fields like short_description, category, risk, and assignment_group. The agent returns the CHG number immediately.
Can the agent search the knowledge base for solutions?
Absolutely. The search_knowledge tool searches across all published knowledge articles using keyword or category filters, returning relevant articles with their KB numbers and resolution steps.
Does it support custom tables beyond the standard ITSM modules?
Yes. The query_table tool works with any ServiceNow table — standard or custom (u_ prefixed). Pass the table name and your SysParm filters, and the agent handles pagination and field expansion automatically.
How does Pydantic AI discover MCP tools?
Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.
Does Pydantic AI validate MCP tool responses?
Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.
Can I switch LLM providers without changing MCP code?
Absolutely. Pydantic AI abstracts the model layer. your ServiceNow MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai