diff --git a/dev/flux-kustomization.yaml b/dev/flux-kustomization.yaml
index 7489dd5..526b7da 100644
--- a/dev/flux-kustomization.yaml
+++ b/dev/flux-kustomization.yaml
@@ -28,6 +28,11 @@ spec:
       BACKEND_AUDIENCE: '["classic-models-api"]'
       BACKEND_SCOPES: '[]'
       API_RATE_LIMIT_MINUTE: "60"
+      # Read volume for an MCP caller, per identity per minute. An agent
+      # reads a thousand records in seconds where a person clicks ten; this is
+      # the only control that notices. Generous enough that a conversational
+      # turn never meets it, tight enough that a loop does.
+      MCP_READS_PER_MINUTE: "60"
       # The URI path is the collector's routing key: Fluent Bit tags the
       # record `catalog` and turns that into the Loki label domain=catalog.
       AUDIT_LOG_ENDPOINT: http://audit-log-collector.observability.svc.cluster.local/catalog
diff --git a/kong/kustomization.yaml b/kong/kustomization.yaml
index afc03db..1d7e17a 100644
--- a/kong/kustomization.yaml
+++ b/kong/kustomization.yaml
@@ -17,6 +17,7 @@ resources:
   - mcp/consumergroups.yaml
   - mcp/ai-mcp-proxy.yaml
   - mcp/openid-connect.yaml
+  - mcp/rate-limiting.yaml
   - mcp/audit-log.yaml
   - mcp/audit-log-body-capture.yaml
   - mcp/audit-log-body-capture-bindings.yaml
diff --git a/kong/mcp/pluginbindings.yaml b/kong/mcp/pluginbindings.yaml
index 18fbbc3..a3d532f 100644
--- a/kong/mcp/pluginbindings.yaml
+++ b/kong/mcp/pluginbindings.yaml
@@ -51,3 +51,21 @@ spec:
       group: configuration.konghq.com
       kind: KongService
       name: ${NAME}-catalog-mcp
+---
+apiVersion: configuration.konghq.com/v1alpha1
+kind: KongPluginBinding
+metadata:
+  name: ${NAME}-catalog-mcp-rate-limiting-binding
+  namespace: ${NAMESPACE}
+spec:
+  controlPlaneRef:
+    type: konnectNamespacedRef
+    konnectNamespacedRef:
+      name: ${CONTROL_PLANE_REF_NAME}
+  pluginRef:
+    name: ${NAME}-catalog-mcp-rate-limiting
+  targets:
+    routeRef:
+      group: configuration.konghq.com
+      kind: KongRoute
+      name: ${NAME}-catalog-mcp
diff --git a/kong/mcp/rate-limiting.yaml b/kong/mcp/rate-limiting.yaml
new file mode 100644
index 0000000..e728498
--- /dev/null
+++ b/kong/mcp/rate-limiting.yaml
@@ -0,0 +1,37 @@
+# A read-volume cap per caller identity.
+#
+# A scope authorises a read and says nothing about volume. An agent reads a
+# thousand records in seconds where a person clicks ten, and the difference is
+# invisible to every control the estate had until now — the token is valid, the
+# tool is permitted, the ACL passes.
+#
+# `identifier: credential` keys the counter on what the openid-connect plugin
+# published as the caller's credential, which is the `sub` claim: the end user,
+# whoever is asking on their behalf. So an agent looping under one person's
+# identity spends that person's budget, and cannot spend everyone's.
+apiVersion: configuration.konghq.com/v1
+kind: KongPlugin
+metadata:
+  name: ${NAME}-catalog-mcp-rate-limiting
+  namespace: ${NAMESPACE}
+plugin: rate-limiting-advanced
+config:
+  identifier: credential
+  # Per-route counters. Sharing a namespace across domains would let a busy
+  # catalog exhaust the budget for payments.
+  namespace: ${NAME}-catalog-mcp
+  strategy: local
+  sync_rate: -1
+  window_type: sliding
+  window_size:
+    - 60
+  limit:
+    - ${MCP_READS_PER_MINUTE}
+  # Loud rather than silent: a caller that hits the cap is told, and the headers
+  # say when it resets. An agent that only sees a 429 with no Retry-After
+  # retries immediately and makes it worse.
+  hide_client_headers: false
+  error_code: 429
+  error_message: >-
+    Read volume limit reached for this identity. This is a cap on how much can
+    be read per minute, not a permission problem.