OpenAI ChatGPT Enterprise Unusual Codex MCP Tool Call

Last updated 11 days ago on 2026-10-06

Created 11 days ago on 2026-10-06

About

Detects the first ChatGPT Enterprise Codex MCP tool name used by a given user email within an organization in the rule history window. Codex MCP tools can query external systems and pull organizational data into an agent session. Alerting on first-seen organization, user, and tool triples highlights new or unexpected connector usage rather than every routine approved tool call.

Tags

Domain: GenAIPlatform: OpenAIData Source: OpenAI ChatGPT EnterpriseService: OpenAI ChatGPT EnterpriseUse Case: Threat DetectionUse Case: UEBARule Type: New TermsTactic: CollectionMitre Atlas: AML.T0085Language: kuery

Severity

medium

Risk Score

MITRE ATT&CK™

Collection (TA0009)(external, opens in a new tab or window)

↳ Data from Information Repositories (T1213)(external, opens in a new tab or window)

False Positive Examples

Engineers enable approved Codex MCP connectors for GitHub, Slack, ticketing, and internal tools during normal development. Validate the tool name, connector, and whether the integration matches an approved workflow.

License

Elastic License v2(external, opens in a new tab or window)

Definition

Rule Type: New Terms Rule
Integration Pack: Prebuilt Security Detection Rules
Index Patterns: logs-openai_chatgpt_enterprise.codex_log-*
Related Integrations: openai_chatgpt_enterprise(external, opens in a new tab or window)
Query

✄𐘗text code block:
✄𐘗data_stream.dataset: "openai_chatgpt_enterprise.codex_log" and
    event.action: "app_mcp_call" and
    organization.id: * and
    user.email: * and
    gen_ai.tool.name: *

Install detection rules in Elastic Security

Detect OpenAI ChatGPT Enterprise Unusual Codex MCP Tool Call in the Elastic Security detection engine by installing this rule into your Elastic Stack.

To setup this rule, check out the installation guide for Prebuilt Security Detection Rules(external, opens in a new tab or window).