Use Common Language Expressions (CEL) expressions to secure access to AI resources.

About CEL-based RBAC link

Agentgateway proxies use CEL expressions to match requests or responses on specific parameters, such as a request header or source address. If the request matches the condition, it is allowed. Requests that do not match any of the conditions are denied.

For an overview of supported CEL expressions, see the agentgateway docs.

Before you begin link

Set up an agentgateway proxy.

Set up access to Gemini link

Configure access to an LLM provider such as Gemini. You can use any other LLM provider, an MCP server, or an agent to try out CEL-based RBAC.

1. Save your Gemini API key as an environment variable. To retrieve your API key, log in to the Google AI Studio and select API Keys.

     export GOOGLE_KEY=<your-api-key>
     

2. Create a secret to authenticate to Google.

     kubectl apply -f - <<EOF
   apiVersion: v1
   kind: Secret
   metadata:
     name: google-secret
     namespace: gloo-system
   type: Opaque
   stringData:
     Authorization: $GOOGLE_KEY
   EOF
     

3. Create a Backend resource to define the Gemini destination.

     kubectl apply -f- <<EOF
   apiVersion: gateway.kgateway.dev/v1alpha1
   kind: Backend
   metadata:
     labels:
       app: agentgateway
     name: google
     namespace: gloo-system
   spec:
     ai:
       llm:
        gemini:
             apiVersion: v1beta
             authToken:
               kind: SecretRef
               secretRef:
                 name: google-secret
             model: gemini-2.5-flash-lite
     type: AI
   EOF
     

   Review the following table to understand this configuration.

   Setting	Description
   gemini	The Gemini AI provider.
   apiVersion	The API version of Gemini that is compatible with the model that you plan to use. In this example, you must use v1beta because the gemini-2.5-flash-lite model is not compatible with the v1 API version. For more information, see the Google AI docs.
   authToken	The authentication token to use to authenticate to the LLM provider. The example refers to the secret that you created in the previous step.
   model	The model to use to generate responses. In this example, you use the gemini-2.5-flash-lite model. For more models, see the Google AI docs.

4. Create an HTTPRoute resource to route requests to the Gemini Backend. Note that Gloo Gateway automatically rewrites the endpoint that you set up (such as /gemini) to the appropriate chat completion endpoint of the LLM provider for you, based on the LLM provider that you set up in the Backend resource.

     kubectl apply -f- <<EOF
   apiVersion: gateway.networking.k8s.io/v1
   kind: HTTPRoute
   metadata:
     name: google
     namespace: gloo-system
   spec:
     parentRefs:
       - name: agentgateway
     rules:
     - matches:
       - path:
           type: PathPrefix
           value: /gemini
       backendRefs:
       - name: google
         group: gateway.kgateway.dev
         kind: Backend
   EOF
     

6. Send a request to the LLM provider API. Verify that the request succeeds and that you get back a response from the chat completion API.

     curl -vik "$INGRESS_GW_ADDRESS/gemini" -H content-type:application/json  -d '{
     "model": "",
     "messages": [
      {"role": "user", "content": "Explain how AI works in simple terms."}
    ]
   }'
     

     curl -vik "localhost:8080/gemini" -H content-type:application/json  -d '{
     "model": "",
     "messages": [
      {"role": "user", "content": "Explain how AI works in simple terms."}
    ]
   }'
     

   Example output:

     {"id":"aGLEaMjbLp6p_uMPopeAoAc",
   "choices":
     [{"index":0,"message":{
         "content":"Imagine teaching a dog a trick.  You show it what to do, reward it when it's right, and correct it when it's wrong.  Eventually, the dog learns.\n\nAI is similar.  We \"teach\" computers by showing them lots of examples.  For example, to recognize cats in pictures, we show it thousands of pictures of cats, labeling each one \"cat.\"  The AI learns patterns in these pictures – things like pointy ears, whiskers, and furry bodies – and eventually, it can identify a cat in a new picture it's never seen before.\n\nThis learning process uses math and algorithms (like a secret code of instructions) to find patterns and make predictions.  Some AI is more like a dog learning tricks (learning from examples), and some is more like following a very detailed recipe (following pre-programmed rules).\n\nSo, in short: AI is about teaching computers to learn from data and make decisions or predictions, just like we teach dogs tricks.\n",
         "role":"assistant"
         },
      "finish_reason":"stop"
      }],
    "created":1757700714,
    "model":"gemini-1.5-flash-latest",
    "object":"chat.completion",
    "usage":{
        "prompt_tokens":8,
        "completion_tokens":205,
        "total_tokens":213
        }
   }
     

Set up RBAC permissions link

1. Create a GlooTrafficPolicy with your CEL rules. The following example allows requests with the x-llm: gemini header.

     kubectl apply -f- <<EOF
   apiVersion: gloo.solo.io/v1alpha1
   kind: GlooTrafficPolicy
   metadata:
     name: rbac
     namespace: gloo-system
     labels:
       app: agentgateway
   spec:
     targetRefs:
     - group: gateway.networking.k8s.io
       kind: HTTPRoute
       name: google
     rbac:
       policy:
         matchExpressions:
           - "request.headers['x-llm'] == 'gemini'"
   EOF
     

2. Send a request to the LLM provider API without the llm header. Verify that the request is denied with a 403 HTTP response code.

     curl -vik "$INGRESS_GW_ADDRESS:8080/gemini" -H content-type:application/json  -d '{
     "model": "",
     "messages": [
      {"role": "user", "content": "Explain how AI works in simple terms."}
    ]
   }'
     

     curl -vik "localhost:8080/gemini" -H content-type:application/json  -d '{
     "model": "",
     "messages": [
      {"role": "user", "content": "Explain how AI works in simple terms."}
    ]
   }'
     

   Example output:

     * upload completely sent off: 109 bytes
   < HTTP/1.1 403 Forbidden
   HTTP/1.1 403 Forbidden
   < content-type: text/plain
   content-type: text/plain
   < content-length: 20
   content-length: 20
   < 
   
   * Connection #0 to host localhost left intact
   authorization failed
     

3. Send another request to the LLM provider. This time, you include the llm header. Verify that the request succeeds with a 200 HTTP response code.

     curl -vik "$INGRESS_GW_ADDRESS:8080/gemini" \
     -H "content-type: application/json" \
     -H "x-llm: gemini" -d '{
     "model": "",
     "messages": [
      {"role": "user", "content": "Explain how AI works in simple terms."}
    ]
   }'
     

     curl -vik "localhost:8080/gemini" \
     -H "content-type: application/json" \
     -H "x-llm: gemini" -d '{
     "model": "",
     "messages": [
      {"role": "user", "content": "Explain how AI works in simple terms."}
    ]
   }'
     

Cleanup link

  kubectl delete GlooTrafficPolicy -n gloo-system -l app=agentgateway
kubectl delete httproute google -n gloo-system
kubectl delete backend google -n gloo-system
kubectl delete secret google-secret -n gloo-system
  

link