How is this different from connecting Microsoft Sentinel 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 Microsoft Sentinel MCP API changes?

We track the Microsoft Sentinel 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 Microsoft Sentinel 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 Microsoft Sentinel?

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 Microsoft Sentinel MCP server myself?

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

Connect Microsoft Sentinel MCP to your AI agents, securely.

Q: Is Microsoft Sentinel MCP secure?

The server itself exposes 26 tools, and some of them can write to your Microsoft Sentinel 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 Microsoft Sentinel.

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

Get started for free

Get a demo

Try Microsoft Sentinel MCP now

What your agents can ask once Microsoft Sentinel MCP is connected.

Select the tools your AI agents can call

26 tools from the Microsoft Sentinel MCP schema.

Showing 26 tools

ListIncidentsreadLists security incidents filtered by date range, severity, status, assigned analyst and investigation state.
ListAlertsreadLists the alerts associated with incidents or filtered independently.
GetIncidentByIdreadThis tool retrieves a security incident by ID, including its properties, correlated alerts, and metadata such as status, severity, classification, and timestamps.
GetDefenderFileAlertsreadList all security alerts generated by a specific file in your organization, including historical and active alerts.
ListDefenderInvestigationsreadList automated investigation cases in Defender for Endpoint. Use filters for state, target device, start time, or triggering alert ID.
GetDefenderInvestigationreadGet details of a specific automated investigation, including state, timestamps, target device, and triggering alert.
GetDefenderIpAlertsreadList all security alerts in the organization that are related to a specified IP address.
GetDefenderMachineAlertsreadList all security alerts associated with a specific device for a device-centric view of threats.
ListDefenderRemediationActivitiesreadList remediation tasks and their execution status across devices. Each remediation activity corresponds to a security recommendation or task.
GetDefenderRemediationActivityreadGet detailed remediation task information, including execution status, results, and affected devices.
ListUserRelatedAlertsreadList all security alerts associated with a specific user account. This information is essential for user-centric threat investigations and behavior analysis.
FetchAdvancedHuntingTablesOverviewreadLists the advanced hunting tables available, so a query targets the right ones.
FetchAdvancedHuntingTablesDetailedSchemareadGets the detailed schema of advanced hunting tables. Run this before writing KQL.
RunAdvancedHuntingQueryreadRuns an advanced hunting query in KQL across supported Microsoft Defender tables.
ListDefenderIndicatorsreadList tenant indicators of compromise (IOCs) in Microsoft Defender for Endpoint. Use filters for type, value, action, and severity.
GetDefenderFileInforeadGet file details such as hashes, size, type, publisher, signer certificate info, and global prevalence with first and last seen timestamps.
GetDefenderFileStatisticsreadGet organizational file prevalence statistics, including the number of devices where the file was observed.
GetDefenderFileRelatedMachinesreadList all devices that encountered a specific file to assess its spread in your environment.
GetDefenderIpStatisticsreadGet statistics for a given IP address, including the number of distinct devices that communicated with it.
GetDefenderMachinereadGet detailed information about a specific Defender for Endpoint device, including operating system details, health status, risk score, and exposure level.
GetDefenderMachineLoggedOnUsersreadList accounts that signed in to a device. For each user, the API provides context such as the account username and domain.
GetDefenderMachineVulnerabilitiesreadList discovered security vulnerabilities on a device with Common Vulnerabilities and Exposures (CVE) details and risk assessment scores.
FindDefenderMachineByIpreadList all devices that communicated with a specific internal IP address in the time range of 15 minutes before and after the given timestamp, for network mapping and lateral movement analysis.
ListUserRelatedMachinesreadList all devices where a specific user has active or recent sign-in sessions. Use this tool to track user activity and analyze lateral movement.
ListDefenderMachinesByVulnerabilityreadList all devices affected by a specific CVE vulnerability. This tool is critical for patch management prioritization.
ListDefenderVulnerabilitiesBySoftwarereadList vulnerabilities that affect specific software on a specific device for targeted vulnerability assessment.

What Microsoft Sentinel MCP exposes

Microsoft Sentinel MCP groups its 26 tools into 3 categories, each with a suggested starting policy.

All 26 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Triage	Listing and reading incidents, alerts and the evidence attached to them	Read	Incident data is highly sensitive; limit to the SOC
Hunting	Advanced hunting tables, their schema and KQL query execution	Read	Fetch the schema before running KQL; watch query cost on the data lake
Entities	Entity risk analysis for users, devices, files and IP addresses	Read	Entity profiles combine data about real people; restrict access

Connect Microsoft Sentinel 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 Microsoft Sentinel
Find Microsoft Sentinel 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 Microsoft Sentinel MCP or block it. You allow the exact tools each agent can call, one by one.

Microsoft Sentinel MCP	26 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 26 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 Microsoft Sentinel 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.	Microsoft Sentinel MCP26 documented tools.
Coding assistants	Connection & credentialsper user	Triage11 tools
Internal copilots	Tool access policiesdeny by default	Entities11 tools
Workflow automations	Request & response inspectioninline	Hunting4 tools
Compatible MCP clients	Activity monitoringalerts and logs