Skip to content

Connectors · MSP & PSA

Microsoft Defender for Cloud MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Microsoft Defender for Cloud and the rest of your systems. It gives your agent 277 Microsoft Defender for Cloud actions (178 reads, 68 writes and 31 that wait for a confirmation) and holds the Microsoft Defender for Cloud credential itself, so the agent never does. It paces Microsoft Defender for Cloud'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/mcp
the first call
do {  action: "azure_defender_for_cloud.assessments_metadata.list",  intent: "check which Microsoft Defender for Cloud account is connected"}# Get metadata information on all assessment types · read · 1 upstream call
  • 277actionsin one signed file
  • 178readlook, never change
  • 68writecreate and update
  • 31wait for a yesdestructive, confirmed first

Set up

Connect Microsoft Defender for Cloud in three steps.

  1. 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
  2. 02

    Connect Microsoft Defender for Cloud.

    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) id of a service principal with Security Reader or Security Admin on the subscription
    • client_secretEntra client secret
    • tenant_idYour Microsoft Defender for Cloud tenant id
    account { op: "connections.requirements", service: "azure_defender_for_cloud" }
    # free: exactly what to paste, and what is found for you
  3. 03

    Make the first call. Check before a write.

    Ask in plain words; Claude picks the action. Before anything changes, check validates the call and prices it, for free.

    do    { action: "azure_defender_for_cloud.assessments_metadata.list" }# get metadata information on all assessment types · read · 1 upstream callcheck { action: "azure_defender_for_cloud.alerts.simulate", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

Microsoft Defender for Cloud 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
200 calls a minute, per connection
API covered
Microsoft Defender for Cloud (secure score, recommendations, alerts, Defender plans, regulatory compliance, JIT, DevOps security) API Azure Resource Manager Microsoft.Security, one api-version per resource type: stable/2026-07-01/pricings.json (2026-07-01), stable/2026-07-01/batchPricings.json (2026-07-01), stable/2020-01-01/secureScore.json (2020-01-01), stable/2025-05-04/security-Assessment.json (2025-05-04), preview/2019-01-01-preview/subAssessments.json (2019-01-01-preview), stable/2022-01-01/alerts.json (2022-01-01), preview/2019-01-01-preview/alertsSuppressionRules.json (2019-01-01-preview), preview/2019-01-01-preview/regulatoryCompliance.json (2019-01-01-preview), stable/2024-08-01/security-SecurityStandards.json (2024-08-01), preview/2022-01-01-preview/security-Governance.json (2022-01-01-preview), stable/2020-01-01/security-SecuritySolutions.json (2020-01-01), preview/2015-06-01-preview/locations.json (2015-06-01-preview), preview/2015-06-01-preview/tasks.json (2015-06-01-preview), preview/2017-08-01-preview/security-LegacySettings.json (2017-08-01-preview), preview/2021-05-01-preview/softwareInventories.json (2021-05-01-preview), preview/2021-10-01-preview/mdeOnboardings.json (2021-10-01-preview), preview/2022-07-01-preview/applications.json (2022-07-01-preview), preview/2023-01-01-preview/securityOperators.json (2023-01-01-preview), preview/2026-04-01-preview/security-SqlVulnerabilityAssessments.json (2026-04-01-preview), preview/2023-02-15-preview/sensitivitySettings.json (2023-02-15-preview), preview/2023-05-01-preview/healthReports.json (2023-05-01-preview), preview/2023-12-01-preview/security-Automations.json (2023-12-01-preview), preview/2026-08-01-preview/securityConnectors.json (2026-08-01-preview), stable/2025-03-01/securityConnectorsDevOps.json (2025-03-01), stable/2025-06-01/defenderForStorageSettings.json (2025-06-01), stable/2025-06-01/operations.json (2025-06-01), stable/2017-08-01/complianceResults.json (2017-08-01), stable/2019-01-01/advancedThreatProtectionSettings.json (2019-01-01), stable/2019-08-01/security-IoTSecurity.json (2019-08-01), stable/2022-05-01/settings.json (2022-05-01), stable/2023-05-01/ServerVulnerabilityAssessmentsSettings.json (2023-05-01), stable/2023-11-15/apiCollections.json (2023-11-15), stable/2026-01-01/privateLinks.json (2026-01-01), stable/2026-08-01/datascanners.json (2026-08-01), preview/2026-09-01-preview/serviceEntitlements.json (2026-09-01-preview), preview/2026-09-16-preview/serviceEntitlementSettings.json (2026-09-16-preview)management.azure.com
Built from
Microsoft Defender for Cloud's documentation, read 23 October 2026GitHublearn.microsoft.com
Service file
Version 1.0.0, signed (Ed25519)
Cached reads
173 of 178 reads, for up to 5 minutes; a write clears what it affects
Shared entities
2, so ask can line Microsoft Defender for Cloud 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 Defender for Cloud.

277 actions in 76 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

  • 178readlook, never change
  • 68writecreate and update
  • 31destructivewait for a confirmation
  1. Alerts

    15

    6 read · 9 write · 0 destructive

    List all the alerts that are associated with the subscription · Get an alert that is associated with a subscription · List all the alerts that are associated with the resource group · List all the alerts that are associated with the resource group that are stored in a specific location

  2. Jit network access policies

    8

    5 read · 2 write · 1 destructive

    Policies for protecting resources using Just-in-Time access control · Policies for protecting resources using Just-in-Time access control for the subscription, location · Policies for protecting resources using Just-in-Time access control for the subscription, location · Policies for protecting resources using Just-in-Time access control for the subscription, location

  3. Automations

    7

    4 read · 2 write · 1 destructive

    Lists all the security automations in the specified subscription · Lists all the security automations in the specified resource group · Retrieves information about the model of a security automation · Validates the security automation model before create or update

  4. Service entitlements

    7

    4 read · 2 write · 1 destructive

    Lists service entitlements in a resource group · Lists service entitlements in a subscription · Gets a service entitlement · Gets the result of a long-running operation performed on a service entitlement

  5. Tasks

    7

    5 read · 2 write · 0 destructive

    Recommended tasks that will help improve the security of the subscription proactively · Recommended tasks that will help improve the security of the subscription proactively · Recommended tasks that will help improve the security of the subscription proactively · Recommended tasks that will help improve the security of the subscription proactively

  6. API collections

    6

    4 read · 1 write · 1 destructive

    Gets a list of onboarded Azure API Management APIs · Gets a list of API collections within a resource group · Gets a list of API collections within a subscription · Gets an onboarded Azure API Management API

  7. Assessments metadata

    6

    4 read · 1 write · 1 destructive

    Get metadata information on all assessment types · Get metadata information on all assessment types in a specific subscription · Get metadata information on an assessment type · Get metadata information on an assessment type in a specific subscription

  8. Governance rules

    6

    3 read · 2 write · 1 destructive

    Get a list of all relevant governance rules over a scope · Get a specific governance rule for the requested scope by ruleId · Get governance rules long run operation result for the requested scope by ruleId and operationId · Execute a governance rule

68 more areas · 215 actions
  • Iot security solutions 6
  • Private links 6
  • Security connectors 6
  • Service entitlement settings 6
  • Azure devops orgs 5
  • Defender for storage 5
  • Devops configurations 5
  • SQL vulnerability assessment baseline rules 5
  • Workspace settings 5
  • Alerts suppression rules 4
  • Applications 4
  • Assessments 4
  • Azure devops projects 4
  • Azure devops repos 4
  • Custom recommendations 4
  • Data scanners 4
  • Device security groups 4
  • Governance assignments 4
  • Pricings 4
  • Private endpoint connections 4
  • Security connector applications 4
  • Security contacts 4
  • Security operators 4
  • Security standards 4
  • Server vulnerability assessments 4
  • Server vulnerability assessments settings 4
  • SQL vulnerability assessment scans 4
  • Standard assignments 4
  • Allowed connections 3
  • Auto provisioning settings 3
  • Batch pricings 3
  • Discovered security solutions 3
  • External security solutions 3
  • Github owners 3
  • Gitlab groups 3
  • Information protection policies 3
  • Iot security solutions analytics aggregated alert 3
  • Sensitivity settings 3
  • Settings 3
  • Software inventories 3
  • SQL vulnerability assessment settings 3
  • Sub assessments 3
  • Topologies 3
  • Advanced threat protection 2
  • Compliance results 2
  • Compliances 2
  • Github repos 2
  • Gitlab projects 2
  • Health reports 2
  • Iot security solution analytics 2
  • Iot security solutions analytics recommendation 2
  • Locations 2
  • Mde onboardings 2
  • Private link resources 2
  • Regulatory compliance assessments 2
  • Regulatory compliance controls 2
  • Regulatory compliance standards 2
  • Secure score control definitions 2
  • Secure score controls 2
  • Secure scores 2
  • Security solutions 2
  • Security solutions reference data 2
  • SQL vulnerability assessment scan results 2
  • Devops operation results 1
  • Gitlab subgroups 1
  • Operations 1
  • Resource groups 1
  • Subscriptions 1

Top actions

The Microsoft Defender for Cloud API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 8 of Microsoft Defender for Cloud's 8 action names are shared with at least one other connector, so an agent learns them once.

ActionWhat it doesEffectSame name in
azure_defender_for_cloud.governance_rules.listGet a list of all relevant governance rules over a scopeGet a list of all relevant governance rules over a scope.readsecurity.policy.list36 connectors
azure_defender_for_cloud.alerts.listList all the alerts that are associated with the subscriptionList all the alerts that are associated with the subscription.readsecurity.alert.list22 connectors
azure_defender_for_cloud.alerts.get_subscription_levelGet an alert that is associated with a subscriptionGet an alert that is associated with a subscription.readsecurity.alert.get21 connectors
azure_defender_for_cloud.secure_score_controls.listGet all security controls within a scopeGet all security controls within a scope.readsecurity.control.list6 connectors
azure_defender_for_cloud.standard_assignments.listGet a list of all relevant standard assignments over a scopeGet a list of all relevant standard assignments over a scope.readsecurity.policy_assignment.list5 connectors
azure_defender_for_cloud.regulatory_compliance_standards.listSupported regulatory compliance standards details and stateSupported regulatory compliance standards details and state.readsecurity.framework.list5 connectors
azure_defender_for_cloud.resource_groups.listList the resource groups in a subscriptionList the resource groups in a subscription.readinfra.resource_group.list19 connectors
azure_defender_for_cloud.regulatory_compliance_standards.getSupported regulatory compliance details state for selected standardSupported regulatory compliance details state for selected standard.readsecurity.framework.get4 connectors
azure_defender_for_cloud.alerts.simulateSimulate security alertsSimulate security alerts.writethis connector
azure_defender_for_cloud.jit_network_access_policies.initiateInitiate a JIT access from a specific Just-in-Time policy configurationInitiate a JIT access from a specific Just-in-Time policy configuration.writethis connector
azure_defender_for_cloud.defender_for_storage.start_malware_scanInitiate a Defender for Storage malware scan for the specified storage accountInitiate a Defender for Storage malware scan for the specified storage account.writethis connector
azure_defender_for_cloud.pricings.deleteDeletes a provided Microsoft Defender for Cloud pricing configuration in a specific resourceDeletes a provided Microsoft Defender for Cloud pricing configuration in a specific resource.destructivethis connector

Try it

Prompts to paste into Claude.

Each one names the Microsoft Defender for Cloud actions it will call, so you know what it reads and what it changes before you send it.

  1. Readread

    Which Microsoft Defender for Cloud alerts are open right now? Group them by service.

    callsazure_defender_for_cloud.alerts.list

  2. Writewrite

    Simulate security alerts in Microsoft Defender for Cloud. Show me exactly what you will send before you save it.

    callsazure_defender_for_cloud.alerts.simulate

Governance for Microsoft Defender for Cloud

Destructive actions wait for a yes.

31 Microsoft Defender for Cloud actions are destructive. The first 10:

  • Deletes a provided Microsoft Defender for Cloud pricing configuration in a specific resourceazure_defender_for_cloud.pricings.delete
  • Delete a security assessment on your resourceazure_defender_for_cloud.assessments.delete
  • Deletes a security automationazure_defender_for_cloud.automations.delete
  • Delete an Application over a given scopeazure_defender_for_cloud.applications.delete
  • Deletes a data scanner resource for the specified scopeazure_defender_for_cloud.data_scanners.delete
  • Delete a private link resourceazure_defender_for_cloud.private_links.delete
  • Delete a Governance rule over a given scopeazure_defender_for_cloud.governance_rules.delete
  • Delete security contact configurations for the subscriptionazure_defender_for_cloud.security_contacts.delete
  • Delete Microsoft Defender for Cloud securityOperator in the subscriptionazure_defender_for_cloud.security_operators.delete
  • Delete a security standard over a given scopeazure_defender_for_cloud.security_standards.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.

doazure_defender_for_cloud.pricings.deleteconfirm_policy: human

Deletes a provided Microsoft Defender for Cloud pricing configuration in a specific resource?

intent: the user asked me to deletes a provided Microsoft Defender for Cloud pricing configuration in a specific resource

run suspended · waiting for a named person · key azure-defender-for-cloud-agent cannot confirm itself
In the console, or from an emailed signed link.
a key for this connector
account {  op: "keys.create", name: "azure-defender-for-cloud-agent",  allowed_actions: ["azure_defender_for_cloud.*"], cap_calls: 2000,  confirm_policy: "human_for_writes",  approval_rules: [    { match: "azure_defender_for_cloud.pricings.delete", approver: "[email protected]" },    { match: "azure_defender_for_cloud.assessments.delete", approver: "[email protected]" },    { match: "azure_defender_for_cloud.automations.delete", approver: "[email protected]" }  ]}
Illustrative. Scoped to Microsoft Defender for Cloud only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person.

Cost

What Microsoft Defender for Cloud costs on actionlake.

Every Microsoft Defender for Cloud action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Microsoft Defender for Cloud 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 277 Microsoft Defender for Cloud actions
  • 89actions pageeach page of a long list is one call
  • 173reads can be cacheda cache hit costs nothing
  • 100,000calls a month, freepaid plans from US$49 a month for 250,000

See pricing

Action index

Every Microsoft Defender for Cloud action.

277 actions by area: the id your agent calls, what it does, and its effect.

Alerts15
  • azure_defender_for_cloud.alerts.get_subscription_levelGet an alert that is associated with a subscriptionread
  • azure_defender_for_cloud.alerts.listList all the alerts that are associated with the subscriptionread
  • and 13 more in this area
Jit network access policies8
  • azure_defender_for_cloud.jit_network_access_policies.getPolicies for protecting resources using Just-in-Time access control for the subscription, locationread
  • azure_defender_for_cloud.jit_network_access_policies.listPolicies for protecting resources using Just-in-Time access controlread
  • and 6 more in this area
Automations7
  • azure_defender_for_cloud.automations.getRetrieves information about the model of a security automationread
  • azure_defender_for_cloud.automations.listLists all the security automations in the specified subscriptionread
  • and 5 more in this area
Service entitlements7
  • azure_defender_for_cloud.service_entitlements.getGets a service entitlementread
  • azure_defender_for_cloud.service_entitlements.get_operation_resultGets the result of a long-running operation performed on a service entitlementread
  • and 5 more in this area
Tasks7
  • azure_defender_for_cloud.tasks.get_resource_group_level_taskRecommended tasks that will help improve the security of the subscription proactivelyread
  • azure_defender_for_cloud.tasks.get_subscription_level_taskRecommended tasks that will help improve the security of the subscription proactivelyread
  • and 5 more in this area
API collections6
  • azure_defender_for_cloud.api_collections.get_by_azure_api_management_serviceGets an onboarded Azure API Management APIread
  • azure_defender_for_cloud.api_collections.list_by_azure_api_management_serviceGets a list of onboarded Azure API Management APIsread
  • and 4 more in this area
Assessments metadata6
  • azure_defender_for_cloud.assessments_metadata.getGet metadata information on an assessment typeread
  • azure_defender_for_cloud.assessments_metadata.get_in_subscriptionGet metadata information on an assessment type in a specific subscriptionread
  • and 4 more in this area
Governance rules6
  • azure_defender_for_cloud.governance_rules.executeExecute a governance rulewrite
  • azure_defender_for_cloud.governance_rules.getGet a specific governance rule for the requested scope by ruleIdread
  • and 4 more in this area
Iot security solutions6
  • azure_defender_for_cloud.iot_security_solutions.getUser this method to get details of a specific IoT Security solution based on solution nameread
  • azure_defender_for_cloud.iot_security_solutions.list_by_resource_groupUse this method to get the list IoT Security solutions organized by resource groupread
  • and 4 more in this area
Private links6
  • azure_defender_for_cloud.private_links.getGet a private link resourceread
  • azure_defender_for_cloud.private_links.listLists all the private links in the specified resource groupread
  • and 4 more in this area
Security connectors6
  • azure_defender_for_cloud.security_connectors.getRetrieves details of a specific security connectorread
  • azure_defender_for_cloud.security_connectors.listLists all the security connectors in the specified subscriptionread
  • and 4 more in this area
Service entitlement settings6
  • azure_defender_for_cloud.service_entitlement_settings.getGets a service entitlement settingread
  • azure_defender_for_cloud.service_entitlement_settings.list_by_resource_groupLists service entitlement settings in a resource groupread
  • and 4 more in this area
Azure devops orgs5
  • azure_defender_for_cloud.azure_devops_orgs.getReturns a monitored Azure DevOps organization resourceread
  • azure_defender_for_cloud.azure_devops_orgs.listReturns a list of Azure DevOps organizations onboarded to the connectorread
  • and 3 more in this area
Defender for storage5
  • azure_defender_for_cloud.defender_for_storage.cancel_malware_scanCancels a Defender for Storage malware scan for the specified storage accountdestructive
  • azure_defender_for_cloud.defender_for_storage.getGets the Defender for Storage settings for the specified storage accountread
  • and 3 more in this area
Devops configurations5
  • azure_defender_for_cloud.devops_configurations.deleteDeletes a DevOps Connectordestructive
  • azure_defender_for_cloud.devops_configurations.getGets a DevOps Configurationread
  • and 3 more in this area
SQL vulnerability assessment baseline rules5
  • azure_defender_for_cloud.sql_vulnerability_assessment_baseline_rules.addSet a list of baseline rules. Will overwrite any previously existing results (for all rules)write
  • azure_defender_for_cloud.sql_vulnerability_assessment_baseline_rules.deleteDeletes a rule from the Baseline of a given databasedestructive
  • and 3 more in this area
Workspace settings5
  • azure_defender_for_cloud.workspace_settings.deleteDeletes the custom workspace settings for this subscriptiondestructive
  • azure_defender_for_cloud.workspace_settings.getSettings about where we should store your security data and logsread
  • and 3 more in this area
Alerts suppression rules4
  • azure_defender_for_cloud.alerts_suppression_rules.deleteDelete dismiss alert rule for this subscriptiondestructive
  • azure_defender_for_cloud.alerts_suppression_rules.getGet dismiss rule, with name: {alertsSuppressionRuleName}, for the given subscriptionread
  • and 2 more in this area
Applications4
  • azure_defender_for_cloud.applications.create_or_updateCreates or update a security application on the given subscriptionwrite
  • azure_defender_for_cloud.applications.deleteDelete an Application over a given scopedestructive
  • and 2 more in this area
Assessments4
  • azure_defender_for_cloud.assessments.create_or_updateCreate a security assessment on your resourcewrite
  • azure_defender_for_cloud.assessments.deleteDelete a security assessment on your resourcedestructive
  • and 2 more in this area
Azure devops projects4
  • azure_defender_for_cloud.azure_devops_projects.create_or_updateCreates or updates a monitored Azure DevOps project resourcewrite
  • azure_defender_for_cloud.azure_devops_projects.getReturns a monitored Azure DevOps project resourceread
  • and 2 more in this area
Azure devops repos4
  • azure_defender_for_cloud.azure_devops_repos.create_or_updateCreates or updates a monitored Azure DevOps repository resourcewrite
  • azure_defender_for_cloud.azure_devops_repos.getReturns a monitored Azure DevOps repository resourceread
  • and 2 more in this area
Custom recommendations4
  • azure_defender_for_cloud.custom_recommendations.create_or_updateCreates or updates a custom recommendation over a given scopewrite
  • azure_defender_for_cloud.custom_recommendations.deleteDelete a custom recommendation over a given scopedestructive
  • and 2 more in this area
Data scanners4
  • azure_defender_for_cloud.data_scanners.create_or_updateCreates or updates a data scanner resource for the specified scopewrite
  • azure_defender_for_cloud.data_scanners.deleteDeletes a data scanner resource for the specified scopedestructive
  • and 2 more in this area
Device security groups4
  • azure_defender_for_cloud.device_security_groups.create_or_updateUse this method to creates or updates the device security group on a specified IoT Hub resourcewrite
  • azure_defender_for_cloud.device_security_groups.deleteUser this method to deletes the device security groupdestructive
  • and 2 more in this area
Governance assignments4
  • azure_defender_for_cloud.governance_assignments.create_or_updateCreates or updates a governance assignment on the given subscriptionwrite
  • azure_defender_for_cloud.governance_assignments.deleteDelete a GovernanceAssignment over a given scopedestructive
  • and 2 more in this area
Pricings4
  • azure_defender_for_cloud.pricings.deleteDeletes a provided Microsoft Defender for Cloud pricing configuration in a specific resourcedestructive
  • azure_defender_for_cloud.pricings.getGet the Defender plans pricing configurations of the selected scope (valid scopes are resource id or a subscription id)read
  • and 2 more in this area
Private endpoint connections4
  • azure_defender_for_cloud.private_endpoint_connections.create_or_updateUpdate the state of specified private endpoint connection associated with the private linkwrite
  • azure_defender_for_cloud.private_endpoint_connections.deleteDeletes the specified private endpoint connection associated with the private linkdestructive
  • and 2 more in this area
Security connector applications4
  • azure_defender_for_cloud.security_connector_applications.create_or_updateCreates or update a security Application on the given security connectorwrite
  • azure_defender_for_cloud.security_connector_applications.deleteDelete an Application over a given scopedestructive
  • and 2 more in this area
Security contacts4
  • azure_defender_for_cloud.security_contacts.createCreate security contact configurations for the subscriptionwrite
  • azure_defender_for_cloud.security_contacts.deleteDelete security contact configurations for the subscriptiondestructive
  • and 2 more in this area

Security operators 4Security standards 4Server vulnerability assessments 4Server vulnerability assessments settings 4SQL vulnerability assessment scans 4Standard assignments 4Allowed connections 3Auto provisioning settings 3Batch pricings 3Discovered security solutions 3External security solutions 3Github owners 3Gitlab groups 3Information protection policies 3Iot security solutions analytics aggregated alert 3Sensitivity settings 3Settings 3Software inventories 3SQL vulnerability assessment settings 3Sub assessments 3Topologies 3Advanced threat protection 2Compliance results 2Compliances 2Github repos 2Gitlab projects 2Health reports 2Iot security solution analytics 2Iot security solutions analytics recommendation 2Locations 2Mde onboardings 2Private link resources 2Regulatory compliance assessments 2Regulatory compliance controls 2Regulatory compliance standards 2Secure score control definitions 2Secure score controls 2Secure scores 2Security solutions 2Security solutions reference data 2SQL vulnerability assessment scan results 2Devops operation results 1Gitlab subgroups 1Operations 1Resource groups 1Subscriptions 1

This index shows a sample of each area. All 277 actions, with their inputs and prices, are in the catalogue, which a free sandbox key can search.

Questions

The Microsoft Defender for Cloud MCP server, answered.

Is there a Microsoft Defender for Cloud MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 277 Microsoft Defender for Cloud actions across alerts, jit network access policies, automations and service entitlements, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Microsoft Defender for Cloud.

What do I need to connect Microsoft Defender for Cloud?

Entra application (client) id of a service principal with Security Reader or Security Admin on the subscription and Entra client secret. Plus your tenant id. The free call account { op: "connections.requirements", service: "azure_defender_for_cloud" } lists exactly what to paste.

Can an AI agent delete or change things in Microsoft Defender for Cloud?

Only if its key allows it, and only with an explicit confirmation. 31 Microsoft Defender for Cloud actions are destructive, including deletes a provided Microsoft Defender for Cloud pricing configuration in a specific resource, delete a security assessment on your resource and deletes a security automation. 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 Defender for Cloud API limit?

actionlake paces every call to the limits in the Microsoft Defender for Cloud service file: 200 calls a minute per connection. Repeated reads are answered from cache (173 Microsoft Defender for Cloud actions can be), which never reaches Microsoft Defender for Cloud.

What does a Microsoft Defender for Cloud action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (89 Microsoft Defender for Cloud actions page). Cache hits, searches, dry runs and calls Microsoft Defender for Cloud 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 Defender for Cloud API does it cover?

The Microsoft Defender for Cloud (secure score, recommendations, alerts, Defender plans, regulatory compliance, JIT, DevOps security) API Azure Resource Manager Microsoft.Security, one api-version per resource type: stable/2026-07-01/pricings.json (2026-07-01), stable/2026-07-01/batchPricings.json (2026-07-01), stable/2020-01-01/secureScore.json (2020-01-01), stable/2025-05-04/security-Assessment.json (2025-05-04), preview/2019-01-01-preview/subAssessments.json (2019-01-01-preview), stable/2022-01-01/alerts.json (2022-01-01), preview/2019-01-01-preview/alertsSuppressionRules.json (2019-01-01-preview), preview/2019-01-01-preview/regulatoryCompliance.json (2019-01-01-preview), stable/2024-08-01/security-SecurityStandards.json (2024-08-01), preview/2022-01-01-preview/security-Governance.json (2022-01-01-preview), stable/2020-01-01/security-SecuritySolutions.json (2020-01-01), preview/2015-06-01-preview/locations.json (2015-06-01-preview), preview/2015-06-01-preview/tasks.json (2015-06-01-preview), preview/2017-08-01-preview/security-LegacySettings.json (2017-08-01-preview), preview/2021-05-01-preview/softwareInventories.json (2021-05-01-preview), preview/2021-10-01-preview/mdeOnboardings.json (2021-10-01-preview), preview/2022-07-01-preview/applications.json (2022-07-01-preview), preview/2023-01-01-preview/securityOperators.json (2023-01-01-preview), preview/2026-04-01-preview/security-SqlVulnerabilityAssessments.json (2026-04-01-preview), preview/2023-02-15-preview/sensitivitySettings.json (2023-02-15-preview), preview/2023-05-01-preview/healthReports.json (2023-05-01-preview), preview/2023-12-01-preview/security-Automations.json (2023-12-01-preview), preview/2026-08-01-preview/securityConnectors.json (2026-08-01-preview), stable/2025-03-01/securityConnectorsDevOps.json (2025-03-01), stable/2025-06-01/defenderForStorageSettings.json (2025-06-01), stable/2025-06-01/operations.json (2025-06-01), stable/2017-08-01/complianceResults.json (2017-08-01), stable/2019-01-01/advancedThreatProtectionSettings.json (2019-01-01), stable/2019-08-01/security-IoTSecurity.json (2019-08-01), stable/2022-05-01/settings.json (2022-05-01), stable/2023-05-01/ServerVulnerabilityAssessmentsSettings.json (2023-05-01), stable/2023-11-15/apiCollections.json (2023-11-15), stable/2026-01-01/privateLinks.json (2026-01-01), stable/2026-08-01/datascanners.json (2026-08-01), preview/2026-09-01-preview/serviceEntitlements.json (2026-09-01-preview), preview/2026-09-16-preview/serviceEntitlementSettings.json (2026-09-16-preview) at management.azure.com. It is built from Microsoft Defender for Cloud's documentation as read on 23 October 2026. 277 actions in 76 areas, each one in the signed service file (version 1.0.0).

Does actionlake keep my Microsoft Defender for Cloud data, and where?

actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to 5 minutes, 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 Defender for Cloud 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 Defender for Cloud today.

Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free.