ServiceNow MCP. Manage every incident and asset from a single chat window.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
ServiceNow MCP Server connects your AI agent to your entire ITSM backbone. Manage everything—incidents, service requests, change orders, and CMDB records—using natural conversation.
Instead of navigating complex dashboards, you can simply tell your agent what needs fixing or tracking.
What your AI agents can do
Count records
Gets the total number of records from any specified ServiceNow table, useful for quick metrics.
Create record
Creates a brand new record in core tables like Incident, Change Request, or Service Catalog items using JSON fields.
Delete record
Deletes an existing ServiceNow record. Note: this action is irreversible and requires confirmation.
List, query, or update incidents based on priority, status, or assignment group.
Query the CMDB for specific configuration items and map out how different assets relate to each other.
Create, list, or review change requests, ensuring proper documentation and tracking of approvals.
Submit service catalog requests and monitor their status through the approval pipeline.
Find relevant knowledge articles or look up user profiles, group memberships, and roles across the organization.
Run specific queries against any ServiceNow table using filtered parameters (SysParm) for maximum flexibility.
Ask AI about this MCP
Supported MCP Clients
OAuth 2.0 Compatible Gemini Waiting for input…
ServiceNow MCP Server: 10 Tools for IT Operations
These ten tools let you programmatically read, write, update, and query every core record type in your ServiceNow environment using simple text prompts.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using ServiceNow on Vinkius019d7606count records
Gets the total number of records from any specified ServiceNow table, useful for quick metrics.
019d7606create record
Creates a brand new record in core tables like Incident, Change Request, or Service Catalog items using JSON fields.
019d7606delete record
Deletes an existing ServiceNow record. Note: this action is irreversible and requires confirmation.
019d7606get record
Retrieves all field data for a single ServiceNow record using its unique system ID (sys_id).
019d7606list change requests
Lists change requests, allowing filtering by state, risk level, or type.
019d7606list incidents
Retrieves a list of incidents, filterable by priority, status, assignment group, or custom fields.
019d7606query cmdb
Queries the CMDB for specific configuration items (like servers or applications) using common names or IDs.
019d7606query table
Runs a flexible query against virtually any ServiceNow table, supporting dot-walking to fetch related field data.
019d7606search knowledge
Searches the official ServiceNow Knowledge Base for matching articles and provides their KB numbers.
019d7606update record
Modifies an existing record, allowing you to specify only the fields that need changing.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with ServiceNow, then connect any of our 4,800+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,800+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by ServiceNow. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 10 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Triage shouldn't mean jumping through five different tabs.
Today, if a P1 incident hits, you have to open the ticket dashboard, filter by priority 1, check the assignment group, manually see who last touched it, and then potentially jump to the CMDB tab just to see what systems are linked. It's a painful, multi-step process that loses critical time.
With this MCP server, you just tell your agent: 'Show me all P1 incidents related to the main payment API.' The agent handles the `list_incidents` call and cross-references it with `query_cmdb` in one go. You get the answer—the list of affected tickets and assets—without ever clicking a single dashboard button.
ServiceNow MCP Server: Automate your change process.
Manually managing changes means logging into ServiceNow to create the request, making sure the risk level is correct, and then checking who needs to approve it—all of which requires careful data entry. A missed field or wrong state can halt a critical deployment.
Now, you simply ask your agent: 'Draft a low-risk change request for the database patch.' The server uses `create_record`, populating the necessary fields and kicking off the workflow instantly. It's not just drafting; it's starting the entire operational lifecycle.
What you can do with this MCP connector
Listen up. This ServiceNow MCP Server hooks your AI agent right into your entire IT service management (ITSM) backbone. You're not stuck clicking through some dusty dashboard; you just talk to your agent, and it handles the whole messy lifecycle—incidents, changes, requests, CMDB data. It lets your agent read, write, update, or query every core record type in your system using natural conversation.
Triage and Tracking Incidents
When something breaks, you need answers fast. Your agent can pull up a list of incidents by checking priority, status, or the assignment group assigned to them (list_incidents). If you know the unique ID, it'll grab every piece of data associated with that ticket using get_record. You don't just read it—you update it.
Your agent can modify existing records using update_record, so you only tell it which fields need changing. Need to track open tickets by SLA breach status? No sweat.
Managing Changes and Assets (CMDB)
Change control is a headache, but this handles it. You'll use the server to list change requests, filtering them down by risk level or state (list_change_requests). If you need to push through a new change, your agent can create a brand-new record right into core tables like Change Request using create_record.
For assets, the system queries the CMDB for specific configuration items—think servers or apps—using query_cmdb, letting you map out exactly how different pieces of hardware relate to each other.
Service Fulfillment and Raw Data Power
Need a new piece of software or service? Your agent can submit those requests by creating records in the Service Catalog, monitoring their status as they move through approvals. For maximum flexibility when none of the pre-built tools cut it, you've got query_table. This lets your agent run specific queries against virtually any ServiceNow table—you can even do dot-walking to fetch related data fields that aren't in the main record.
You can also get a quick metric count for any table using count_records. If you need to pull user profiles, group memberships, or roles across the whole organization, your agent handles it.
Knowledge and Maintenance Tools
If someone asks how something works, your agent searches the official ServiceNow Knowledge Base (search_knowledge) and spits out matching articles right away. You can also delete records if they're totally obsolete using delete_record, though remember that action is irreversible, so you gotta confirm it first.
How It All Connects
Your AI client uses the Model Context Protocol (MCP) to talk to this server. The agent doesn't just guess; it translates your conversational commands into specific tool calls against your live data. When you use create_record, you pass structured JSON fields, making sure everything is logged correctly. If the system needs to pull detailed information for a single record, it uses the unique sys_id with get_record.
You can modify records using update_record or create them from scratch with create_record. The flexibility of this setup means you're never limited by just listing incidents; you can query any table and fetch any data point you want.
019d7606-8d14-724c-8de9-a94231dc89b1 
How ServiceNow MCP Works
- 1 Subscribe to the server and provide your ServiceNow instance URL and necessary credentials.
- 2 Your AI client recognizes the available tools (e.g.,
list_incidents,query_cmdb) via MCP. - 3 You state a goal in natural language ('Find all P1 incidents unassigned'). The agent executes the required tool calls, returning actionable data.
The bottom line is that your AI agent becomes an operational command center for ServiceNow, handling complex tasks without you needing to navigate Fiori dashboards or write code.
Who Is ServiceNow MCP For?
This server is built for ops engineers and service managers who spend too much time clicking through tickets, manually cross-referencing asset data in CMDB, or struggling with multi-step change requests. If your job requires deep interaction with the ServiceNow platform's records, this saves you hours of context switching.
Uses list_incidents and update_record to triage P1 tickets quickly, check SLA compliance, and assign ownership without touching the GUI.
Runs query_cmdb to map service dependencies before proposing a change, then uses create_record for the change request itself.
Uses search_knowledge and get_record to pull up relevant guides or update user records instantly while chatting with an end-user.
What Changes When You Connect
- Faster Triage: Instead of running complex reports, use
list_incidentsto instantly get all open P1 tickets assigned to you. You see exactly what needs attention immediately. - Accurate Impact Assessment: Don't guess which systems are affected by a change. Run
query_cmdbto trace relationships between applications and servers before proposing any update. - Zero-Click Documentation: Need to know the steps for an issue? Use
search_knowledge. Your agent finds relevant articles instantly, saving you time digging through internal documentation portals. - Full Audit Trail Visibility: When creating changes, use
list_change_requeststo review who approved what and when. It gives you a clear, auditable path of every intended change. - Dynamic Data Retrieval: Don't rely on one view. Use the highly flexible
query_tabletool to execute custom queries across any table type with dot-walking support.
Real-World Use Cases
Need to identify all vulnerable servers for a patch.
The Ops Engineer needs to know which servers are running outdated software. They ask the agent, 'Show me all CMDB records where the OS is older than 2024.' The agent runs query_cmdb, lists the affected assets, and provides the list of sys_ids for follow-up.
A P1 incident needs immediate escalation.
The Help Desk Analyst sees a high-priority ticket. They ask the agent to 'Update INC0012345 status to Investigating and assign it to Tier 3.' The agent uses update_record immediately, logging the change without opening a single ServiceNow page.
A new service needs tracking and approval.
The Product Owner asks the agent to 'Create a request for a new payment gateway integration.' The agent uses create_record targeting the sc_request table, populating all necessary fields and initiating the approval workflow.
Investigating why an asset failed.
The Analyst needs to know if the failure is related to a specific network component. They ask the agent to 'List the CI relationships for the main database server.' The agent runs query_cmdb and maps out all dependent assets, narrowing down the root cause.
The Tradeoffs
Trying to solve multi-step problems in one shot.
The user just asks: 'Fix the database issue.' The agent can't know if they need to check assets, create an incident, or update a record. This leads to vague tool calls and failure.
→
Break it down into steps. First, run query_cmdb on the affected asset name. Second, use list_incidents to see existing tickets. Third, if necessary, call create_record for a new incident with all gathered data.
Assuming record existence before updating.
The user asks the agent to 'Update this ticket's owner.' But they forget the sys_id. The tool fails because it doesn't know which record you mean, wasting time.
→
Always verify the ID first. Use get_record with the suspect sys_id to confirm it exists and is visible before attempting any update_record or delete_record action.
Treating CMDB as a general database.
Trying to query for non-asset data (like user names) using only the query_cmdb tool. This is wrong because the scope limits you to configuration items.
→
Use query_table when querying generic data like user profiles or general tickets. Reserve query_cmdb specifically for structured asset and CI relationships.
When It Fits, When It Doesn't
Use this server if your core job involves managing records, tracking service lifecycles, or mapping IT assets within ServiceNow. The power is in the breadth of tools: you can create, read, update, query CMDBs, and search knowledge—all from one chat interface.
Don't use it if you just need to run a simple report that doesn't involve creating or changing records; those reports are better handled by native reporting features. Also, if your data management is entirely siloed outside of ServiceNow (e.g., in Jira and GitHub), this server won't help—you'll need an integration layer specific to those tools.
Always remember: the difference between query_table and query_cmdb matters. Use query_cmdb when you need dependency mapping; use query_table for general data lookups.
Common Questions About ServiceNow MCP
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.
When using the MCP Server, what information do I need to connect my instance? +
You must provide your ServiceNow instance URL and active credentials during setup. This connection authorizes your AI client to perform actions on your specific environment.
How does the get_record tool retrieve all fields from a single record? +
The get_record tool requires only the sys_id of the record you want. It pulls every associated field value, giving you a complete data dump for that specific item.
Is using the delete_record tool irreversible, and how should I use it safely? +
Yes, deleting records is permanent and cannot be undone within the system. Always confirm with your AI client before executing this action to prevent accidental data loss.
Can I query_cmdb to map dependencies between assets and applications? +
Absolutely. The query_cmdb tool lets you search configuration items (CIs) and explore the relationships mapped across your infrastructure, helping you analyze potential impacts before changes.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.