Merge branch 'master' into ROB-1323-cluster-status-init-crash-take-2

Author: RoiGlinik

Dockerfile

@@ -53,6 +53,7 @@ RUN find "/app/venv/lib/python3.11/site-packages/kubernetes/client/models/" -typ
 # Final stage
 FROM python:3.11-slim
 
+
 ENV ENV_TYPE=DEV
 ENV PYTHONUNBUFFERED=1
 ENV VIRTUAL_ENV=/app/venv
@@ -74,7 +75,8 @@ RUN apt-get update \
 # Patching CVE-2024-32002
 RUN git config --global core.symlinks false
 
-# Remove setuptools-65.5.1 installed from python:3.11-slim base image as fix for CVE-2024-6345 until image will be updated
+# Temporary setuptools CVE fix untill python:3.12-slim image will be used.
+RUN rm -rf /usr/local/lib/python3.11/ensurepip/_bundled/setuptools-65.5.0-py3-none-any.whl
 RUN rm -rf /usr/local/lib/python3.11/site-packages/setuptools-65.5.1.dist-info
 
 COPY --from=builder /app/venv /venv

docs/configuration/holmesgpt/remote_mcp_servers.rst

@@ -41,6 +41,165 @@ Example : MCP server configuration
 
         helm upgrade robusta robusta/robusta --values=generated_values.yaml --set clusterName=<YOUR_CLUSTER_NAME>
 
+
+Example : Working with Stdio MCP servers
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+MCP currently supports three transport mechanisms: stdio, Server-Sent Events (SSE), and Streamable HTTP.
+At this time, HolmesGPT is compatible only with MCP servers that use SSE.
+However, many existing MCP servers—such as Dynatrace MCP—rely exclusively on the stdio transport.
+To overcome this incompatibility, tools like Supergateway can act as a bridge by converting stdio-based MCPs into SSE-compatible endpoints.
+
+For this demo we will use
+  * `Dynatrace MCP <https://github.com/dynatrace-oss/dynatrace-mcp>`_ .
+  * `Supergateway <https://github.com/supercorp-ai/supergateway>`_ - runs MCP stdio-based servers over SSE.
+
+Check out supergatway docs to find out other useful flags.
+
+**See it in action** 
+
+.. raw:: html
+
+  <div>
+      <a href="https://www.loom.com/share/1b290511b79942c7b1d672a2a4cde105">
+        <img style="max-width:300px;" src="https://cdn.loom.com/sessions/thumbnails/1b290511b79942c7b1d672a2a4cde105-ed4eed3f9d70b125-full-play.gif">
+      </a>
+  </div>
+
+1. Run stdio MCP as SSE
+""""""""""""""""""""""""""""""
+.. md-tab-set::
+
+  .. md-tab-item:: Docker 
+    
+    This command runs the Dynatrace MCP server locally via Docker using Supergateway to wrap it with SSE support.
+    Credentials (e.g., API keys) should be stored in a .env file passed to Docker using --env-file.
+    you can change `"npx -y @dynatrace-oss/dynatrace-mcp-server@latest /"` to your specific MCP.
+
+    .. code-block:: shell
+
+      docker run --env-file .env -it --rm -p  8003:8003 supercorp/supergateway \
+      --stdio "npx -y @dynatrace-oss/dynatrace-mcp-server@latest /" \
+      --port 8003 \
+      --logLevel debug 
+
+    Once the container starts, you should see logs similar to:
+
+    .. code-block:: shell
+
+      [supergateway] Starting...
+      [supergateway] Supergateway is supported by Supermachine (hosted MCPs) - https://supermachine.ai
+      [supergateway]   - outputTransport: sse
+      [supergateway]   - Headers: (none)
+      [supergateway]   - port: 8003
+      [supergateway]   - stdio: npx -y @dynatrace-oss/dynatrace-mcp-server@latest /
+      [supergateway]   - ssePath: /sse
+      [supergateway]   - messagePath: /message
+      [supergateway]   - CORS: disabled
+      [supergateway]   - Health endpoints: (none)
+      [supergateway] Listening on port 8003
+      [supergateway] SSE endpoint: http://localhost:8003/sse
+      [supergateway] POST messages: http://localhost:8003/message
+
+  .. md-tab-item:: Kubernetes Pod
 
+    | This will run dynatrace MCP server as a pod in your cluster.
+    | credentials are passed as env vars.
+
+    .. code-block:: yaml
+
+        apiVersion: v1
+        kind: Pod
+        metadata:
+          name: dynatrace-mcp
+          labels:
+            app: dynatrace-mcp
+        spec:
+          containers:
+            - name: supergateway
+              image: supercorp/supergateway
+              env:
+                - name: DT_ENVIRONMENT
+                  value: https://abcd1234.apps.dynatrace.com
+                - name: OAUTH_CLIENT_ID
+                  value: dt0s02.SAMPLE
+                - name: OAUTH_CLIENT_SECRET
+                  valueFrom:
+                    secretKeyRef:
+                      name: dynatrace-credentials
+                      key: client_secret                   
+              ports:
+                - containerPort: 8003
+              args:
+                - "--stdio"
+                - "npx -y @dynatrace-oss/dynatrace-mcp-server@latest /"
+                - "--port"
+                - "8003"
+                - "--logLevel"
+                - "debug"
+              stdin: true
+              tty: true
+        ---
+        apiVersion: v1
+        kind: Service
+        metadata:
+          name: dynatrace-mcp
+        spec:
+          selector:
+            app: dynatrace-mcp
+          ports:
+            - protocol: TCP
+              port: 8003
+              targetPort: 8003
+          type: ClusterIP
+
+
+2. Add MCP server to holmes config.
+""""""""""""""""""""""""""""""""""""""
+
+With the MCP server running in SSE mode, we need to let HolmesGPT know of the mcp server.
+Use this config according to your use case.
+
+**Configuration:**
+
+.. md-tab-set::
 
+  .. md-tab-item:: Holmes CLI
+
+    Use a config file, and pass it when running cli commands.
+
+    **custom_toolset.yaml:**
+
+    .. code-block:: yaml
+
+      mcp_servers:          
+        mcp_server_1:
+          description: "Dynatrace observability platform. Bring real-time observability data directly into your development workflow."
+          url: "http://localhost:8003/sse"
+
+    You can now use Holmes via the CLI with your configured MCP server. For example:
+
+    .. code-block:: bash
+
+      holmes ask -t custom_toolset.yaml  "Using dynatrace what issues do I have in my cluster?"  
+
+  .. md-tab-item:: Robusta Helm Chart
+
+    **Helm Values:**
+
+    .. code-block:: yaml
+
+      holmes:
+        mcp_servers:          
+          mcp_server_1:
+            description: "Dynatrace observability platform. Bring real-time observability data directly into your development workflow."
+            url: "http://dynatrace-mcp.default.svc.cluster.local:8003"
+
+        
+    Update your Helm values with the provided YAML configuration, then apply the changes with Helm upgrade:
+
+    .. code-block:: bash
+
+        helm upgrade robusta robusta/robusta --values=generated_values.yaml --set clusterName=<YOUR_CLUSTER_NAME>
 
+    After the deployment is complete, you can open the HolmesGPT chat in the Robusta SaaS UI and ask questions like *Using dynatrace what issues do I have in my cluster?*.