add E2E testing framework #26
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -57,6 +57,10 @@ helm-lint: ## Run helm lint for Helm chart | |
| test: ## Run unit tests | ||
| $(GOTEST) -v ./... | ||
|
|
||
| .PHONY: e2e-test | ||
| e2e-test: ## Run E2E tests | ||
| @cd e2e-tests && ./scripts/run-tests.sh | ||
|
|
||
| .PHONY: test-coverage-and-junit | ||
| test-coverage-and-junit: ## Run unit tests with coverage and junit output | ||
| go install github.com/jstemmer/go-junit-report/[email protected] | ||
|
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,105 @@ | ||
| # StackRox MCP E2E Testing | ||
|
|
||
| End-to-end tests for the StackRox MCP server using [gevals](https://github.com/genmcp/gevals). | ||
|
|
||
| ## Prerequisites | ||
|
|
||
| - Go 1.25+ | ||
| - Google Cloud Project with Vertex AI enabled (for Claude agent) | ||
| - OpenAI API Key (for LLM judge) | ||
| - StackRox API Token | ||
|
|
||
| ## Setup | ||
|
|
||
| ### 1. Build gevals | ||
|
|
||
| ```bash | ||
| cd e2e-tests | ||
| ./scripts/build-gevals.sh | ||
| ``` | ||
|
|
||
| ### 2. Configure Environment | ||
|
|
||
| Create `.env` file: | ||
|
|
||
| ```bash | ||
| # Required: GCP Project for Vertex AI (Claude agent) | ||
| ANTHROPIC_VERTEX_PROJECT_ID=<GCP Project ID> | ||
|
|
||
| # Required: StackRox Central API Token | ||
| STACKROX_MCP__CENTRAL__API_TOKEN=<StackRox API Token> | ||
|
|
||
| # Required: OpenAI API Key (for LLM judge) | ||
| OPENAI_API_KEY=<OpenAI API Key> | ||
|
|
||
| # Optional: Vertex AI region (defaults to us-east5) | ||
| CLOUD_ML_REGION=us-east5 | ||
|
|
||
| # Optional: Judge configuration (defaults to OpenAI) | ||
| JUDGE_MODEL_NAME=gpt-5-nano | ||
| ``` | ||
|
|
||
| ## Running Tests | ||
|
|
||
| ```bash | ||
| ./scripts/run-tests.sh | ||
| ``` | ||
|
|
||
| Results are saved to `gevals/gevals-stackrox-mcp-e2e-out.json`. | ||
|
|
||
| ### View Results | ||
|
|
||
| ```bash | ||
| # Summary | ||
| jq '.[] | {taskName, taskPassed}' gevals/gevals-stackrox-mcp-e2e-out.json | ||
|
|
||
| # Tool calls | ||
| jq '.[].callHistory[] | {toolName, arguments}' gevals/gevals-stackrox-mcp-e2e-out.json | ||
| ``` | ||
|
|
||
| ## Test Cases | ||
|
|
||
| | Test | Description | Tool | | ||
| |------|-------------|------| | ||
| | `list-clusters` | List all clusters | `list_clusters` | | ||
| | `cve-detected-workloads` | CVE detected in deployments | `get_deployments_for_cve` | | ||
| | `cve-detected-clusters` | CVE detected in clusters | `get_clusters_with_orchestrator_cve` | | ||
| | `cve-nonexistent` | Handle non-existent CVE | `get_clusters_with_orchestrator_cve` | | ||
| | `cve-cluster-does-exist` | CVE with cluster filter | `get_clusters_with_orchestrator_cve` | | ||
| | `cve-cluster-does-not-exist` | CVE with cluster filter | `get_clusters_with_orchestrator_cve` | | ||
| | `cve-clusters-general` | General CVE query | `get_clusters_with_orchestrator_cve` | | ||
| | `cve-cluster-list` | CVE across clusters | `get_clusters_with_orchestrator_cve` | | ||
|
|
||
| ## Configuration | ||
|
|
||
| - **`gevals/eval.yaml`**: Main test configuration, agent settings, assertions | ||
| - **`gevals/mcp-config.yaml`**: MCP server configuration | ||
| - **`gevals/tasks/*.yaml`**: Individual test task definitions | ||
|
|
||
| ## How It Works | ||
|
|
||
| Gevals uses a proxy architecture to intercept MCP tool calls: | ||
|
|
||
| 1. AI agent receives task prompt | ||
| 2. Agent calls MCP tool | ||
| 3. Gevals proxy intercepts and records the call | ||
| 4. Call forwarded to StackRox MCP server | ||
| 5. Server executes and returns result | ||
| 6. Gevals validates assertions and response quality | ||
|
|
||
| ## Troubleshooting | ||
|
|
||
| **Tests fail - no tools called** | ||
| - Verify StackRox Central is accessible | ||
| - Check API token permissions | ||
|
|
||
| **Build errors** | ||
| ```bash | ||
| go mod tidy | ||
janisz marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| ./scripts/build-gevals.sh | ||
| ``` | ||
|
|
||
| ## Further Reading | ||
|
|
||
| - [Gevals Documentation](https://github.com/genmcp/gevals) | ||
| - [StackRox MCP Server](../README.md) | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change | ||||
|---|---|---|---|---|---|---|
| @@ -0,0 +1,110 @@ | ||||||
| kind: Eval | ||||||
| metadata: | ||||||
| name: "stackrox-mcp-e2e" | ||||||
| config: | ||||||
| agent: | ||||||
| type: "builtin.claude-code" | ||||||
| model: "claude-sonnet-4-5" | ||||||
| llmJudge: | ||||||
| env: | ||||||
| baseUrlKey: JUDGE_BASE_URL | ||||||
| apiKeyKey: JUDGE_API_KEY | ||||||
| modelNameKey: JUDGE_MODEL_NAME | ||||||
| mcpConfigFile: mcp-config.yaml | ||||||
| taskSets: | ||||||
| # Assertion Fields Explained: | ||||||
| # - toolsUsed: List of tools that MUST be called at least once | ||||||
| # - minToolCalls: Minimum TOTAL number of tool calls across ALL tools (not per-tool) | ||||||
| # - maxToolCalls: Maximum TOTAL number of tool calls across ALL tools (prevents runaway tool usage) | ||||||
| # Example: If maxToolCalls=3, the agent can make up to 3 tool calls total in the test, | ||||||
| # regardless of which tools are called. | ||||||
|
|
||||||
| # Test 1: List clusters | ||||||
| - path: tasks/list-clusters.yaml | ||||||
| assertions: | ||||||
| toolsUsed: | ||||||
| - server: stackrox-mcp | ||||||
| toolPattern: "list_clusters" | ||||||
| minToolCalls: 1 | ||||||
| maxToolCalls: 1 | ||||||
|
|
||||||
| # Test 2: CVE detected in workloads | ||||||
| # Claude does comprehensive CVE checking (orchestrator, deployments, nodes) | ||||||
| - path: tasks/cve-detected-workloads.yaml | ||||||
| assertions: | ||||||
|
Collaborator
There was a problem hiding this comment. Is it possible to define
Contributor
Author
There was a problem hiding this comment. nope, actually we can define glob instead of path and assert tools used for the whole suite (all tasks) and rely on verify and judge to score them |
||||||
| toolsUsed: | ||||||
| - server: stackrox-mcp | ||||||
| toolPattern: "get_deployments_for_cve" | ||||||
| argumentsMatch: | ||||||
| cveName: "CVE-2021-31805" | ||||||
| minToolCalls: 1 | ||||||
| maxToolCalls: 3 | ||||||
|
|
||||||
| # Test 3: CVE detected in clusters - basic | ||||||
| - path: tasks/cve-detected-clusters.yaml | ||||||
| assertions: | ||||||
| toolsUsed: | ||||||
| - server: stackrox-mcp | ||||||
| toolPattern: "get_clusters_with_orchestrator_cve" | ||||||
| argumentsMatch: | ||||||
| cveName: "CVE-2016-1000031" | ||||||
| minToolCalls: 1 | ||||||
| maxToolCalls: 3 | ||||||
|
Collaborator
There was a problem hiding this comment. What
Contributor
Author
There was a problem hiding this comment. nope, tools used are expected (required calls) and max tools calls is the total tools calls |
||||||
|
|
||||||
| # Test 4: Non-existent CVE | ||||||
| # Expects 3 calls because "Is CVE detected in my clusters?" triggers comprehensive check | ||||||
| # (orchestrator, deployments, nodes). The LLM cannot know beforehand if CVE exists. | ||||||
| - path: tasks/cve-nonexistent.yaml | ||||||
| assertions: | ||||||
| toolsUsed: | ||||||
| - server: stackrox-mcp | ||||||
| toolPattern: "get_clusters_with_orchestrator_cve" | ||||||
| argumentsMatch: | ||||||
| cveName: "CVE-2099-00001" | ||||||
| minToolCalls: 1 | ||||||
| maxToolCalls: 3 | ||||||
|
|
||||||
| # Test 5: CVE with specific cluster filter (does exist) | ||||||
| # Claude does comprehensive checking even for single cluster (orchestrator, deployments, nodes) | ||||||
| - path: tasks/cve-cluster-does-exist.yaml | ||||||
| assertions: | ||||||
| toolsUsed: | ||||||
| - server: stackrox-mcp | ||||||
| toolPattern: "list_clusters" | ||||||
| - server: stackrox-mcp | ||||||
| toolPattern: "get_clusters_with_orchestrator_cve" | ||||||
| argumentsMatch: | ||||||
| cveName: "CVE-2016-1000031" | ||||||
| minToolCalls: 2 | ||||||
| maxToolCalls: 4 | ||||||
|
|
||||||
| # Test 6: CVE with specific cluster filter (does not exist) | ||||||
| - path: tasks/cve-cluster-does-not-exist.yaml | ||||||
| assertions: | ||||||
| toolsUsed: | ||||||
| - server: stackrox-mcp | ||||||
| toolPattern: "list_clusters" | ||||||
| minToolCalls: 1 | ||||||
| maxToolCalls: 2 | ||||||
|
Collaborator
There was a problem hiding this comment. LLM should not fetch list of clusters twice:
Suggested change
Contributor
Author
There was a problem hiding this comment. I made it 2 to pass, I think claude decides to get more data sometimes |
||||||
|
|
||||||
| # Test 7: CVE detected in clusters - general | ||||||
| - path: tasks/cve-clusters-general.yaml | ||||||
| assertions: | ||||||
| toolsUsed: | ||||||
| - server: stackrox-mcp | ||||||
| toolPattern: "get_clusters_with_orchestrator_cve" | ||||||
| argumentsMatch: | ||||||
| cveName: "CVE-2021-31805" | ||||||
| minToolCalls: 1 | ||||||
| maxToolCalls: 5 | ||||||
|
|
||||||
| # Test 8: CVE check with cluster list reference | ||||||
| - path: tasks/cve-cluster-list.yaml | ||||||
| assertions: | ||||||
| toolsUsed: | ||||||
| - server: stackrox-mcp | ||||||
| toolPattern: "get_clusters_with_orchestrator_cve" | ||||||
| argumentsMatch: | ||||||
| cveName: "CVE-2024-52577" | ||||||
| minToolCalls: 1 | ||||||
| maxToolCalls: 5 | ||||||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,12 @@ | ||
| mcpServers: | ||
| stackrox-mcp: | ||
| command: go | ||
| args: | ||
| - run | ||
| - ../../cmd/stackrox-mcp/... | ||
| - --config | ||
| - ../stackrox-mcp-e2e-config.yaml | ||
| # API token loaded from parent shell environment (.env file) | ||
| # No env section = full environment inheritance | ||
| # Auto-approve all tools | ||
| enableAllTools: true |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,9 @@ | ||
| kind: Task | ||
| metadata: | ||
| name: "cve-cluster-does-exist" | ||
| difficulty: easy | ||
| steps: | ||
| prompt: | ||
| inline: "Is this CVE-2016-1000031 detected in cluster name staging-central-cluster?" | ||
| verify: | ||
| contains: "A response indicating whether CVE-2016-1000031 is detected in staging-central-cluster" |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,9 @@ | ||
| kind: Task | ||
| metadata: | ||
| name: "cve-cluster-does-not-exist" | ||
| difficulty: easy | ||
| steps: | ||
| prompt: | ||
| inline: "Is this CVE-2024-52577 detected in cluster name prod-hal-9000?" | ||
| verify: | ||
| contains: "A response indicating that CVE-2024-52577 is not detected in prod-hal-9000 cluster, or that the cluster does not exist" |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,9 @@ | ||
| kind: Task | ||
| metadata: | ||
| name: "cve-cluster-list" | ||
| difficulty: easy | ||
| steps: | ||
| prompt: | ||
| inline: "Is this CVE-2024-52577 detected in any of my clusters?" | ||
| verify: | ||
| contains: "A response indicating whether CVE-2024-52577 is detected in clusters" |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,9 @@ | ||
| kind: Task | ||
| metadata: | ||
| name: "cve-clusters-general" | ||
| difficulty: easy | ||
| steps: | ||
| prompt: | ||
| inline: "Is this CVE-2021-31805 detected in my clusters?" | ||
| verify: | ||
| contains: "A response indicating whether CVE-2021-31805 is detected in any clusters, with specific cluster names if detected, or a statement that no clusters have this CVE." |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,9 @@ | ||
| kind: Task | ||
| metadata: | ||
| name: "cve-detected-clusters" | ||
| difficulty: easy | ||
| steps: | ||
| prompt: | ||
| inline: "Is this CVE-2016-1000031 detected in my clusters?" | ||
| verify: | ||
| contains: "A response indicating whether CVE-2016-1000031 is detected in clusters, nodes, or deployments" |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,9 @@ | ||
| kind: Task | ||
| metadata: | ||
| name: "cve-detected-workloads" | ||
| difficulty: easy | ||
| steps: | ||
| prompt: | ||
| inline: "Is this CVE-2021-31805 detected in my workloads?" | ||
| verify: | ||
| contains: "A response indicating whether CVE-2021-31805 is detected in workloads/deployments, with specific deployment names if detected, or a statement that no deployments have this CVE." |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,9 @@ | ||
| kind: Task | ||
| metadata: | ||
| name: "cve-nonexistent" | ||
| difficulty: easy | ||
| steps: | ||
| prompt: | ||
| inline: "Is CVE-2099-00001 detected in my clusters?" | ||
| verify: | ||
| contains: "A response indicating that CVE-2099-00001 is not found or not detected in any clusters" |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,9 @@ | ||
| kind: Task | ||
| metadata: | ||
| name: "list-clusters" | ||
| difficulty: easy | ||
| steps: | ||
| prompt: | ||
| inline: "List my clusters" | ||
| verify: | ||
| contains: "A response containing a list of cluster names" |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,10 @@ | ||
| #!/bin/bash | ||
| set -e | ||
|
|
||
| cd "$(dirname "$0")/.." | ||
|
|
||
| echo "Building gevals from tool dependencies..." | ||
| go build -o bin/gevals github.com/genmcp/gevals/cmd/gevals | ||
janisz marked this conversation as resolved.
Show resolved
Hide resolved
|
||
|
|
||
| echo "gevals built successfully: bin/gevals" | ||
| ./bin/gevals help | ||
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.