Connectors · Identity & security
Microsoft Graph Security (Defender XDR) MCP server for AI agents.
actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Microsoft Graph Security (Defender XDR) and the rest of your systems. It gives your agent 328 Microsoft Graph Security (Defender XDR) actions (236 reads, 68 writes and 24 that wait for a confirmation) and holds the Microsoft Graph Security (Defender XDR) credential itself, so the agent never does. It paces Microsoft Graph Security (Defender XDR)'s limits and records every call.
100,000 free calls a month. No card, no email, no password: press Start a free sandbox on the next screen and keep the key it shows you.
claude mcp add --transport http actionlake https://connect.actionlake.com/mcpdo { action: "m365_graph_security.alerts_v2_list", intent: "check which Microsoft Graph Security (Defender XDR) account is connected"}# List alerts v2 · read · 1 upstream call- 328actionsin one signed file
- 236readlook, never change
- 68writecreate and update
- 24wait for a yesdestructive, confirmed first
Set up
Connect Microsoft Graph Security (Defender XDR) in three steps.
- 01
Add actionlake to Claude.
Run the command once in Claude Code; its consent page can create a free sandbox: 100,000 calls a month, no card. In the Claude app, add a custom connector with the URL below and paste your key on the consent page. Creating a new sandbox from the Claude app is not yet tested by us.
https://connect.actionlake.com/mcp - 02
Connect Microsoft Graph Security (Defender XDR).
OAuth 2.0, client credentials. Paste the app's client id and secret; actionlake fetches and renews the token, and nobody has to sign in. actionlake stores what you paste write-only, sealed under your tenant's key.
client_idEntra application (client) idclient_secretEntra client secrettenant_idYour Microsoft Graph Security (Defender XDR) tenant id
account { op: "connections.requirements", service: "m365_graph_security" } # free: exactly what to paste, and what is found for you - 03
Make the first call. Check before a write.
Ask in plain words; Claude picks the action. Before anything changes,
checkvalidates the call and prices it, for free.do { action: "m365_graph_security.alerts_v2_list" }# list alerts v2 · read · 1 upstream callcheck { action: "m365_graph_security.incidents_update", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent
Microsoft Graph Security (Defender XDR) at a glance
- Sign-in
- OAuth 2.0, client credentials. Paste the app's client id and secret; actionlake fetches and renews the token, and nobody has to sign in.
- You provide
client_idclient_secret- Setup fields
tenant_id- Limits we pace to
- 10,000 calls per 10 minutes, per connection
- API covered
- Microsoft Graph Security (Defender XDR) API v1.0
graph.microsoft.com/v1.0 - Built from
- Microsoft Graph Security (Defender XDR)'s documentation, read 23 October 2026learn.microsoft.com
- Service file
- Version 1.0.0, signed (Ed25519)
- Cached reads
- 236 of 236 reads, for up to an hour; a write clears what it affects
- Shared entities
- 2, so ask can line Microsoft Graph Security (Defender XDR) up with your other systems
- Data
- Processed and stored in Sydney, Australia. No US region yet
Capabilities
What an AI agent can do in Microsoft Graph Security (Defender XDR).
328 actions in 13 areas. Every one carries its effect, so a key can allow the reads and hold the rest.
- 236readlook, never change
- 68writecreate and update
- 24destructivewait for a confirmation
Ediscovery
9142 read · 38 write · 11 destructive
Create ediscovery cases case members · List ediscovery cases case members · Create ediscovery cases · Create ediscovery cases custodians
Threat intelligence
8686 read · 0 write · 0 destructive
List threat intelligence vulnerabilities · Get threat intelligence vulnerabilities · List threat intelligence article indicators · List threat intelligence articles indicators
Records
4728 read · 10 write · 9 destructive
Create labels authorities · List labels authorities · Create labels categories · List labels categories
Attack simulation
3027 read · 2 write · 1 destructive
List attack simulation simulations · Create attack simulation simulations · Get attack simulation simulations · Delete attack simulation simulations
Identity
2214 read · 6 write · 2 destructive
List identities health issues · List identities identity accounts · List identities sensor candidates · List identities sensors health issues
Data governance
1211 read · 1 write · 0 destructive
Data security and governance process content async · Data security and governance protection scopes compute · Data security and governance sensitivity labels compute rights and inheritance · List data security and governance sensitivity labels
Privacy
129 read · 3 write · 0 destructive
List subject rights requests approvers · List subject rights requests collaborators · Create subject rights requests · List subject rights requests
Alerts
84 read · 4 write · 0 destructive
List alerts v2 · Get alerts v2 · Update alerts v2 · Create alerts v2 comments
5 more areas · 20 actions
- Incidents 6
- Audit 5
- Secure score 5
- Email 3
- Hunting 1
Top actions
The Microsoft Graph Security (Defender XDR) API, shaped for agents.
The ids your agent types, what each does, and the one name it shares with other systems. 17 of Microsoft Graph Security (Defender XDR)'s 18 action names are shared with at least one other connector, so an agent learns them once.
| Action | What it does | Effect | Same name in |
|---|---|---|---|
m365_graph_security.alerts_v2_listList alerts v2 | Get a list of alert resources created to track suspicious activities in an organization. This operation lets you filter and sort through alerts to create an… | read | security.alert.list22 connectors |
m365_graph_security.incidents_listList incidents | Get a list of incident objects that Microsoft 365 Defender created to track attacks in an organization. Attacks are typically inflicted on different types of… | read | security.incident.list17 connectors |
m365_graph_security.alerts_v2_getGet alerts v2 | Get the properties and relationships of an alert object. | read | security.alert.get21 connectors |
m365_graph_security.incidents_getGet incidents | Retrieve the properties and relationships of an incident object. Attacks are typically inflicted on different types of entities, such as devices, users, and… | read | security.incident.get17 connectors |
m365_graph_security.incidents_updateUpdate incidents | Update the properties of an incident object. | write | security.incident.update13 connectors |
m365_graph_security.audit_log_queries_records_listList audit log queries records | The collection of audit log records retrieved by the query. | read | security.audit_log.list69 connectors |
m365_graph_security.threat_intelligence_vulnerabilities_listList threat intelligence vulnerabilities | Read the properties and relationships of a vulnerability object. | read | security.vulnerability.list14 connectors |
m365_graph_security.secure_score_control_profiles_listList secure score control profiles | Retrieve the properties and relationships of a secureScoreControlProfiles object. | read | security.control.list6 connectors |
m365_graph_security.audit_log_queries_records_getGet audit log queries records | The collection of audit log records retrieved by the query. | read | security.audit_log.get11 connectors |
m365_graph_security.attack_simulation_simulations_createCreate attack simulation simulations | Create an attack simulation campaign for a tenant. | write | security.phishing_simulation.create2 connectors |
m365_graph_security.secure_score_control_profiles_updateUpdate secure score control profiles | Update an editable secureScoreControlProfile object within any integrated solution to change various properties, such as tenantNote. | write | security.control.update5 connectors |
m365_graph_security.attack_simulation_simulations_deleteDelete attack simulation simulations | Delete an attack simulation campaign for a tenant. | destructive | security.phishing_simulation.delete2 connectors |
Try it
Prompts to paste into Claude.
Each one names the Microsoft Graph Security (Defender XDR) actions it will call, so you know what it reads and what it changes before you send it.
- Readread
Which Microsoft Graph Security (Defender XDR) incidents are open, and how long has each been open?
calls
m365_graph_security.incidents_list - Writewrite
Update incidents in Microsoft Graph Security (Defender XDR). Show me exactly what you will send before you save it.
calls
m365_graph_security.incidents_update
Governance for Microsoft Graph Security (Defender XDR)
Destructive actions wait for a yes.
24 Microsoft Graph Security (Defender XDR) actions are destructive. These are all of them:
- Delete attack simulation simulations
m365_graph_security.attack_simulation_simulations_delete - Delete ediscovery cases
m365_graph_security.ediscovery_cases_delete - Delete labels citations
m365_graph_security.labels_citations_delete - Delete labels categories
m365_graph_security.labels_categories_delete - Delete identities sensors
m365_graph_security.identities_sensors_delete - Delete labels authorities
m365_graph_security.labels_authorities_delete - Delete labels departments
m365_graph_security.labels_departments_delete - Delete ediscovery cases tags
m365_graph_security.ediscovery_cases_tags_delete - Delete labels retention labels
m365_graph_security.labels_retention_labels_delete - Delete ediscovery cases searches
m365_graph_security.ediscovery_cases_searches_delete - Delete triggers retention events
m365_graph_security.triggers_retention_events_delete - Delete labels file plan references
m365_graph_security.labels_file_plan_references_delete - Ediscovery cases custodians release
m365_graph_security.ediscovery_cases_custodians_release - Delete ediscovery cases case members
m365_graph_security.ediscovery_cases_case_members_delete - Ediscovery cases searches purge data
m365_graph_security.ediscovery_cases_searches_purge_data - Delete labels categories subcategories
m365_graph_security.labels_categories_subcategories_delete - Collaboration analyzed emails remediate
m365_graph_security.collaboration_analyzed_emails_remediate - Identities identity accounts invoke action
m365_graph_security.identities_identity_accounts_invoke_action - Delete trigger types retention event types
m365_graph_security.trigger_types_retention_event_types_delete - Delete ediscovery cases review sets queries
m365_graph_security.ediscovery_cases_review_sets_queries_delete - Delete ediscovery cases custodians site sources
m365_graph_security.ediscovery_cases_custodians_site_sources_delete - Delete ediscovery cases custodians user sources
m365_graph_security.ediscovery_cases_custodians_user_sources_delete - Ediscovery cases noncustodial data sources release
m365_graph_security.ediscovery_cases_noncustodial_data_sources_release - Delete ediscovery cases custodians unified group sources
m365_graph_security.ediscovery_cases_custodians_unified_group_sources_delete
A destructive action runs only with confirm: true. Under the human policy the agent cannot confirm for itself: the run stops until a named person approves, in the console or from a signed link in an email. The cap on a key is refused before the call is sent, never after.
Delete attack simulation simulations?
intent: the user asked me to delete attack simulation simulations
account { op: "keys.create", name: "m365-graph-security-agent", allowed_actions: ["m365_graph_security.*"], cap_calls: 2000, confirm_policy: "human_for_writes", approval_rules: [ { match: "m365_graph_security.attack_simulation_simulations_delete", approver: "[email protected]" }, { match: "m365_graph_security.ediscovery_cases_delete", approver: "[email protected]" }, { match: "m365_graph_security.labels_citations_delete", approver: "[email protected]" } ]}Cost
What Microsoft Graph Security (Defender XDR) costs on actionlake.
Every Microsoft Graph Security (Defender XDR) action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Microsoft Graph Security (Defender XDR) refused with 401, 403, 429 or a 5xx are free. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.
- 1upstream call per actionall 328 Microsoft Graph Security (Defender XDR) actions
- 93actions pageeach page of a long list is one call
- 236reads can be cacheda cache hit costs nothing
- 100,000calls a month, freepaid plans from US$49 a month for 250,000
Action index
Every Microsoft Graph Security (Defender XDR) action.
328 actions by area: the id your agent calls, what it does, and its effect.
Ediscovery91
m365_graph_security.ediscovery_cases_case_members_createCreate ediscovery cases case memberswritem365_graph_security.ediscovery_cases_case_members_listList ediscovery cases case membersreadm365_graph_security.ediscovery_cases_createCreate ediscovery caseswritem365_graph_security.ediscovery_cases_custodians_createCreate ediscovery cases custodianswritem365_graph_security.ediscovery_cases_case_members_deleteDelete ediscovery cases case membersdestructivem365_graph_security.ediscovery_cases_case_members_getGet ediscovery cases case membersread- and 85 more in this area
Threat intelligence86
m365_graph_security.threat_intelligence_article_indicators_listList threat intelligence article indicatorsreadm365_graph_security.threat_intelligence_articles_indicators_listList threat intelligence articles indicatorsreadm365_graph_security.threat_intelligence_vulnerabilities_getGet threat intelligence vulnerabilitiesreadm365_graph_security.threat_intelligence_vulnerabilities_listList threat intelligence vulnerabilitiesreadm365_graph_security.threat_intelligence_article_indicators_artifact_getGet threat intelligence article indicators artifactreadm365_graph_security.threat_intelligence_article_indicators_getGet threat intelligence article indicatorsread- and 80 more in this area
Records47
m365_graph_security.labels_authorities_createCreate labels authoritieswritem365_graph_security.labels_authorities_listList labels authoritiesreadm365_graph_security.labels_categories_createCreate labels categorieswritem365_graph_security.labels_categories_listList labels categoriesreadm365_graph_security.labels_authorities_deleteDelete labels authoritiesdestructivem365_graph_security.labels_authorities_getGet labels authoritiesread- and 41 more in this area
Attack simulation30
m365_graph_security.attack_simulation_simulations_createCreate attack simulation simulationswritem365_graph_security.attack_simulation_simulations_deleteDelete attack simulation simulationsdestructivem365_graph_security.attack_simulation_simulations_getGet attack simulation simulationsreadm365_graph_security.attack_simulation_simulations_listList attack simulation simulationsreadm365_graph_security.attack_simulation_end_user_notifications_details_getGet attack simulation end user notifications detailsreadm365_graph_security.attack_simulation_end_user_notifications_details_listList attack simulation end user notifications detailsread- and 24 more in this area
Identity22
m365_graph_security.identities_health_issues_listList identities health issuesreadm365_graph_security.identities_identity_accounts_listList identities identity accountsreadm365_graph_security.identities_sensor_candidates_listList identities sensor candidatesreadm365_graph_security.identities_sensors_health_issues_listList identities sensors health issuesreadm365_graph_security.identities_health_issues_getGet identities health issuesreadm365_graph_security.identities_health_issues_updateUpdate identities health issueswrite- and 16 more in this area
Data governance12
m365_graph_security.data_security_and_governance_process_content_asyncData security and governance process content asyncwritem365_graph_security.data_security_and_governance_protection_scopes_computeData security and governance protection scopes computereadm365_graph_security.data_security_and_governance_sensitivity_labels_compute_rights_and_inheritanceData security and governance sensitivity labels compute rights and inheritancereadm365_graph_security.data_security_and_governance_sensitivity_labels_listList data security and governance sensitivity labelsreadm365_graph_security.data_security_and_governance_sensitivity_labels_compute_inheritanceData security and governance sensitivity labels compute inheritancereadm365_graph_security.data_security_and_governance_sensitivity_labels_getGet data security and governance sensitivity labelsread- and 6 more in this area
Privacy12
m365_graph_security.subject_rights_requests_approvers_listList subject rights requests approversreadm365_graph_security.subject_rights_requests_collaborators_listList subject rights requests collaboratorsreadm365_graph_security.subject_rights_requests_createCreate subject rights requestswritem365_graph_security.subject_rights_requests_listList subject rights requestsreadm365_graph_security.subject_rights_requests_approvers_getGet subject rights requests approversreadm365_graph_security.subject_rights_requests_collaborators_getGet subject rights requests collaboratorsread- and 6 more in this area
Alerts8
m365_graph_security.alerts_v2_comments_createCreate alerts v2 commentswritem365_graph_security.alerts_v2_getGet alerts v2readm365_graph_security.alerts_v2_listList alerts v2readm365_graph_security.alerts_v2_updateUpdate alerts v2writem365_graph_security.alerts_getGet alertsreadm365_graph_security.alerts_listList alertsread- and 2 more in this area
Incidents6
m365_graph_security.incidents_alerts_listList incidents alertsreadm365_graph_security.incidents_getGet incidentsreadm365_graph_security.incidents_listList incidentsreadm365_graph_security.incidents_updateUpdate incidentswritem365_graph_security.incidents_alerts_getGet incidents alertsreadm365_graph_security.incidents_merge_incidentsIncidents merge incidentswrite
Audit5
m365_graph_security.audit_log_queries_createCreate audit log querieswritem365_graph_security.audit_log_queries_listList audit log queriesreadm365_graph_security.audit_log_queries_records_getGet audit log queries recordsreadm365_graph_security.audit_log_queries_records_listList audit log queries recordsreadm365_graph_security.audit_log_queries_getGet audit log queriesread
Secure score5
m365_graph_security.secure_score_control_profiles_getGet secure score control profilesreadm365_graph_security.secure_score_control_profiles_listList secure score control profilesreadm365_graph_security.secure_score_control_profiles_updateUpdate secure score control profileswritem365_graph_security.secure_scores_listList secure scoresreadm365_graph_security.secure_scores_getGet secure scoresread
Email3
m365_graph_security.collaboration_analyzed_emails_getGet collaboration analyzed emailsreadm365_graph_security.collaboration_analyzed_emails_listList collaboration analyzed emailsreadm365_graph_security.collaboration_analyzed_emails_remediateCollaboration analyzed emails remediatedestructive
Hunting1
m365_graph_security.run_hunting_queryRun hunting queryread
This index shows a sample of each area. All 328 actions, with their inputs and prices, are in the catalogue, which a free sandbox key can search.
Questions
The Microsoft Graph Security (Defender XDR) MCP server, answered.
Is there a Microsoft Graph Security (Defender XDR) MCP server for Claude?
Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 328 Microsoft Graph Security (Defender XDR) actions across ediscovery, threat intelligence, records and attack simulation, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Microsoft Graph Security (Defender XDR).
What do I need to connect Microsoft Graph Security (Defender XDR)?
Entra application (client) id and Entra client secret. Plus your tenant id. The free call account { op: "connections.requirements", service: "m365_graph_security" } lists exactly what to paste.
Can an AI agent delete or change things in Microsoft Graph Security (Defender XDR)?
Only if its key allows it, and only with an explicit confirmation. 24 Microsoft Graph Security (Defender XDR) actions are destructive, including delete attack simulation simulations, delete ediscovery cases and delete labels citations. Each runs only with confirm: true. Under the human confirm policy, or an approval rule on the key, the run waits until a named person approves it.
Will an AI agent use up my Microsoft Graph Security (Defender XDR) API limit?
actionlake paces every call to the limits in the Microsoft Graph Security (Defender XDR) service file: 10,000 calls per 10 minutes per connection. Repeated reads are answered from cache (236 Microsoft Graph Security (Defender XDR) actions can be), which never reaches Microsoft Graph Security (Defender XDR).
What does a Microsoft Graph Security (Defender XDR) action cost?
One upstream call, the only unit actionlake bills. A list that pages bills one call per page (93 Microsoft Graph Security (Defender XDR) actions page). Cache hits, searches, dry runs and calls Microsoft Graph Security (Defender XDR) refused with 401, 403, 429 or a 5xx are free. The Free plan includes 100,000 calls a month with no card. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.
Which Microsoft Graph Security (Defender XDR) API does it cover?
The Microsoft Graph Security (Defender XDR) API v1.0 at graph.microsoft.com/v1.0. It is built from Microsoft Graph Security (Defender XDR)'s documentation as read on 23 October 2026. 328 actions in 13 areas, each one in the signed service file (version 1.0.0).
Does actionlake keep my Microsoft Graph Security (Defender XDR) data, and where?
actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to an hour, and a write clears the reads it affects. Each run's request and response is kept, sealed, for your plan's trace window: 1 day on Free, 3 days on Starter, 7 days on Pro, 14 days on Team, 30 days on Business and 30 days on Enterprise. Your Microsoft Graph Security (Defender XDR) credential is sealed under your tenant's key, never logged and never returned. Your traffic is not used to train models.
Which AI clients can use it?
Claude Code, tested by us end to end, and the Claude app as a custom connector, tested by us with an existing key. Other MCP clients that support remote servers over Streamable HTTP (MCP revisions 2025-06-18 and 2025-11-25) and OAuth dynamic client registration, or a bearer header, should connect the same way; we have not tested them. Or plain REST, under the same action names.
Give your agent Microsoft Graph Security (Defender XDR) today.
Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free.
