How is this different from connecting ServiceNow MCP directly?

Connected directly, an agent sees every tool the server exposes and holds the credential itself. Through TrustGate you choose which tools each agent gets, and every call is logged against the agent that made it.

What if the ServiceNow MCP API changes?

We track the ServiceNow MCP schema, so the tool catalogue stays current. Tools you have already allowed keep working, and anything new stays denied until you enable it.

Can I give different agents different ServiceNow tools?

Yes. Access is set per agent: one can get a handful of read tools, another the full set. You grant the whole MCP or single tools within it.

Where can I see what my agents did in ServiceNow?

Every call is logged against the agent that made it, with the tool it used. Activity can be sent on to your own monitoring.

Do I need to run the ServiceNow MCP server myself?

No. TrustGate connects to the ServiceNow MCP server and sits in front of it. Your agent only talks to your TrustGate URL, never to ServiceNow directly.

Connect ServiceNow MCP to your AI agents, securely.

Q: Is ServiceNow MCP secure?

The server itself exposes 20 tools, and some of them can write to your ServiceNow account. Behind TrustGate an agent only sees the tools you allow, requests and responses are inspected, and every call is logged. Anything outside the allowlist is denied before it reaches ServiceNow.

One secured endpoint for every ServiceNow call your AI agents make, scoped per user, inspected, and logged.

Get started for free

Get a demo

Try ServiceNow MCP now

What your agents can ask once ServiceNow MCP is connected.

Select the tools your AI agents can call

20 tools from the ServiceNow MCP schema.

Showing 20 tools

sn_itsm_mcp_server.incident.get_detailsreadReturns incident fields for a given incident number; the response is role-aware (fulfillers get the full record, requesters a reduced field set for incidents they own).
sn_itsm_mcp_server.incident.modifywriteUpdates fields on an incident, including work notes, comments, assignee and assignment group, through platform-native APIs.
sn_itsm_mcp_server.incident.search_similarreadSearches for incidents similar to a given incident or description using semantic search and returns ranked results.
sn_itsm_mcp_server.lookup_assignment_groupsreadLooks up available assignment groups and individual assignees.
sn_itsm_mcp_server.lookup_usersreadLooks up users in the system by name, role or group membership.
sn_itsm_mcp_server.incident.search_similar_kbreadSearches similar knowledge base articles for an issue to find content that already documents it or its resolution.
sn_itsm_mcp_server.incident.get_kb_detailsreadRetrieves a published KB article by number or sys_id, with title, knowledge base, state, publish date and full body.
sn_itsm_mcp_server.incident.attach_kbwriteLinks a knowledge base article to an incident as a related reference.
sn_itsm_mcp_server.change.lifecyclewriteCreates and updates change requests, calculates risk, upserts change tasks and creates planned outages.
sn_itsm_mcp_server.change.analyzereadSuggests assignment groups, configuration items, change models and templates, and retrieves risk and impact data for a change.
sn_itsm_mcp_server.change.queryreadReads and searches change requests, aggregates them, and returns state info, schedule conflicts and data quality scores.
sn_itsm_mcp_server.change.relationreadLists a change's tasks, affected CIs, approvals, incidents, problems, outages and applied change policies.
sn_itsm_mcp_server.requester.create_incidentwriteGuides a requester through creating an incident or requesting a catalog item, with knowledge deflection, catalog redirection and duplicate detection.
sn_itsm_mcp_server.requester.check_statusreadReturns the status and details of an incident or requested item (RITM) owned by the authenticated user.
sn_itsm_mcp_server.request.modifywriteAdds a customer-visible comment to a requested item (RITM) owned by the authenticated user.
sn_itsm_mcp_server.oncall.on_call_lookupreadLooks up on-call coverage: who is on call for a group or shift, and the user's next on-call shift.
sn_itsm_mcp_server.oncall.timeoff_requestwriteAnalyzes coverage impact and submits a time-off request from an on-call shift after explicit user confirmation.
sn_itsm_mcp_server.itsm_knowledge_graphreadAnswers structured natural-language questions about ITSM data such as open incidents, change requests and active catalog items.
sn_itsm_mcp_server.get_session_timezonereadReturns the user's session time zone and the current date and time in it.
sn_itsm_mcp_server.task_approval_decisionhigh riskApproves or rejects the caller's oldest pending approval for a change request or requested item.

What ServiceNow MCP exposes

ServiceNow MCP groups its 20 tools into 6 categories, each with a suggested starting policy.

All 20 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Incidents	Incident details and updates, similar-incident search, and assignment group and user lookups	Read / Write	Audit updates; keep customer-visible comments under approval
Knowledge Base	Similar-article search, article details and linking articles to incidents	Read / Write	Allow knowledge lookups; audit article links
Change Management	Change request creation and updates, risk calculation, change tasks and planned outages, suggestions, queries and related records	Read / Write	Require approval for lifecycle writes; changes reach production systems
Employee Requests	Requester incident creation with knowledge deflection, status checks and comments on the user's own requested items	Read / Write	Limit to the authenticated requester's own tickets
On-Call	Who is on call by group or shift, the user's next shift, and time-off requests with coverage analysis	Read / Write	Allow lookups; time-off requests need explicit user confirmation
Common Tools	Natural-language questions over ITSM data, the session time zone, and approval decisions on changes and requested items	Read / Write	Keep approval decisions with a human; they authorise changes and requests

Connect ServiceNow MCP to your AI agent

Four steps, under ten minutes.

01
Sign in to NeuralTrust
Open the NeuralTrust platform, sign in and go to Getting started, then Connect your tools.
02
Choose your agent
When asked which agent you use, pick Claude Code, Codex, Cursor, Windsurf, Copilot or your own code.
03
Connect ServiceNow
Find ServiceNow in the tool list and connect it.
04
Connect your agent
Follow the steps on screen to add the config to your agent, then send the test prompt.

Permissions down to the single tool

You do not allow ServiceNow MCP or block it. You allow the exact tools each agent can call, one by one.

ServiceNow MCP	20 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 20 tools

Tool by toolConnecting the server is not the unit of access. Each tool is granted on its own.
Default denyA tool you have not enabled is never exposed to the agent.
Approval on writesTools that change or delete things can require a human to confirm.

Is ServiceNow MCP secure?

One endpoint instead of raw credentials. Every call is checked against policy and logged.

AI agentsConnect through your MCP client configuration.	NeuralTrustApply controls based on your configuration.	ServiceNow MCP20 documented tools.
Coding assistants	Connection & credentialsper user	Incidents5 tools
Internal copilots	Tool access policiesdeny by default	Change Management4 tools
Workflow automations	Request & response inspectioninline	Knowledge Base3 tools
Compatible MCP clients	Activity monitoringalerts and logs	All other tools8 tools