endpoint_vulnerability \u00b7 POST /endpointVulnerability/filter \u2014 Returns events Required: q, from, size. Allowed values: analyticsEventAction=AttributeAdded|CustomAttributeAdded|OperatingSystemFamilyAdded|OperatingSystemFamilyPathsAdded|FunctionContainerArtifactPathAdded|UserActivatedAccou...
AI agents call endpoint_vulnerability_filter to retrieve information from Vicarius vRx MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and filters vulnerability data from endpoints without modifying, deleting, or executing any operations. It is a data retrieval tool constrained to read-only access, as confirmed by the server's stated 'read-only safety enforcement.' The POST method does not indicate write capability here—it is used to pass query parameters for filtering results. No side effects or state changes occur.
From the tool's definition Tool name 'endpoint_vulnerability_filter' and description 'Returns events' with query parameters (q, from, size) indicates a filtering/search operation. The allowed values are all event types that are retrieved, not modified.
Attacks that exploit this kind of access
endpoint_vulnerability \u00b7 POST /endpointVulnerability/filter \u2014 Returns events Required: q, from, size. Allowed values: analyticsEventAction=AttributeAdded|CustomAttributeAdded|OperatingSystemFamilyAdded|OperatingSystemFamilyPathsAdded|FunctionContainerArtifactPathAdded|UserActivatedAccount|UserAdded|OrganizationInstallationsAdded|UserActivity|IncidentEvent|NotificationIncidentEvent|InsightEvent|InternalServerAttributeScan|InternalServerAttributeScanEndpoints|ApplicationConfigEntryAdded|PublisherAdded|ApplicationAdded|EndpointAdded|ArchitectureAdded|FetchApplicationConfigWithCustomizedLocationFailed|FetchApplicationConfigWithCustomizedLocationSucceed|NotificationSourceAdded|OperatingSystemAdded|ProfilePictureAdded|VulnerabilityAdded|PatchAdded|ProfilePictureFailTooLarge|ProfilePictureFailOnUpload|UpdatedDevices|FetchDevices|NotificationsSentToDevice|NotificationsTrack|FetchNotificationById|ExternalReferenceSourceAdded|ExternalReferenceAdded|ExternalReferenceDisabled|UserAddedPassword|UserChangedPassword|UserForgotPassword|OrganizationAdded|UserAuthenticatedPassword|UserResetPassword|FunctionContainerArtifactAdded|FunctionContainerAdded|CapabilityAdded|OrganizationEndpointPublisherProductProcessesAdded|OrganizationExternalReferenceSourceAdded|PublisherProductCapabilityFunctionsAdded|StatusCheckAdded|CommandAdded|OrganizationEndpointFingerprintAdded|CPEStructureAdded|CPEStructureStatusAdded|CheckAdded|LinkAdded|TagAdded|InternalTagAdded|AttackVectorAdded|CheckCommandsAdded|HashtagAdded|OrganizationHashtagAdded|InternalServerAdded|TaskAdded|TaskEndpointsEventsAdded|OrganizationConfigEntryAdded|OrganizationEndpointConfigEntryAdded|OrganizationEndpointPatchPatchPackagesEntryAdded|OrganizationEndpointAutomationsEntryAdded|OrganizationEndpointLogsAdded|LicenseAgreementAdded|ProductRawEntryAdded|PrivacyPolicyAgreementAdded|UserPrivacyPolicyAgreementAdded|OrganizationEndpointGroup|RuleAdded|PathAdded|OrganizationEndpointPublisherProductProcessInternalTags|ScriptTemplateAdded|AutomationAdded|RoleAdded|ResourceAdded|PrivilegeAdded|RoleResourcePrivilegesAdded|OrganizationTeamAdded|PatchPackageXpatch|AuditLogs|BenchmarkResult|BenchmarkCheckResult|EndpointVulnerabilityEvidence|EndpointVulnerability|CPEInfoEvent|IntegrationAction. It is categorised as a Read tool in the Vicarius vRx MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Vicarius vRx MCP Server MCP server in PolicyLayer and add a rule for endpoint_vulnerability_filter: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Vicarius vRx MCP Server. Nothing to install.
endpoint_vulnerability_filter is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the endpoint_vulnerability_filter rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for endpoint_vulnerability_filter. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
endpoint_vulnerability_filter is provided by the Vicarius vRx MCP Server MCP server (space-c0wboy/vicarius-vrx-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →