diff --git a/rules/ml/ml_windows_anomalous_metadata_process.toml b/rules/ml/ml_windows_anomalous_metadata_process.toml
new file mode 100644
index 000000000..9f6aa5974
--- /dev/null
+++ b/rules/ml/ml_windows_anomalous_metadata_process.toml
@@ -0,0 +1,30 @@
+[metadata]
+creation_date = "2020/09/22"
+ecs_version = ["1.6.0"]
+maturity = "production"
+updated_date = "2020/09/22"
+
+[rule]
+anomaly_threshold = 50
+author = ["Elastic"]
+description = """
+Looks for anomalous access to the metadata service by an unusual process. The metadata service may be targeted in order
+to harvest credentials or user data scripts containing secrets.
+"""
+false_positives = [
+    """
+    A newly installed program or one that runs very rarely as part of a monthly or quarterly workflow could trigger this
+    detection rule.
+    """,
+]
+from = "now-45m"
+interval = "15m"
+license = "Elastic License"
+machine_learning_job_id = "windows_rare_metadata_process"
+name = "Unusual Windows Process Calling the Metadata Service"
+risk_score = 21
+rule_id = "abae61a8-c560-4dbd-acca-1e1438bff36b"
+severity = "low"
+tags = ["Elastic", "ML", "Windows"]
+type = "machine_learning"
+