Comprehensive test of all Bluera Knowledge plugin functionality (MCP tools + slash commands).
Runs comprehensive tests of all Bluera Knowledge plugin functionality including MCP tools and slash commands.
/plugin marketplace add blueraai/bluera-knowledge/plugin install bluera-knowledge@blueraComprehensive test of all Bluera Knowledge plugin functionality (MCP tools + slash commands).
!echo "=== BK Plugin Test ===" && ls -la .bluera/bluera-knowledge/ 2>/dev/null || echo "No BK data dir yet (will be created)"
First, clean up any leftover artifacts from previous test runs (ignore errors if they don't exist):
execute with { command: "store:delete", args: { store: "bk-test-store" } } - ignore "not found" errorsrm -rf .bluera/bluera-knowledge/test-content
First, create test content for indexing:
mkdir -p .bluera/bluera-knowledge/test-content
cat > .bluera/bluera-knowledge/test-content/test-file.md << 'EOF'
# BK Plugin Test File
This file contains unique test content for validating the Bluera Knowledge plugin.
## Test Function
The `validateBKPlugin` function performs comprehensive testing of all plugin features.
It checks MCP connectivity, store operations, search functionality, and cleanup.
Keywords: bluera-knowledge-test, plugin-validation, mcp-test
EOF
Execute each test in order. Mark each as PASS or FAIL.
MCP Connection: Call MCP tool execute with { command: "help" }
List Stores (MCP): Call MCP tool execute with { command: "stores" }
Create Store: Call MCP tool execute with:
{ "command": "store:create", "args": { "name": "bk-test-store", "type": "file", "source": ".bluera/bluera-knowledge/test-content" } }
Store Info: Call MCP tool execute with:
{ "command": "store:info", "args": { "store": "bk-test-store" } }
Index Store: Run CLI command via Bash (MCP's store:index spawns background jobs that don't complete reliably):
node dist/index.js index bk-test-store
Search (MCP): Call MCP tool search with:
{ "query": "validateBKPlugin", "stores": ["bk-test-store"] }
Get Full Context: If search returned results, call MCP tool get_full_context with:
{ "resultId": "<id from search result>" }
Stores Command: Run /bluera-knowledge:stores
Search Command: Run /bluera-knowledge:search "bluera-knowledge-test"
Suggest Command: Run /bluera-knowledge:suggest
Delete Store: Call MCP tool execute with:
{ "command": "store:delete", "args": { "store": "bk-test-store" } }
Remove Test Content: Run bash command:
rm -rf .bluera/bluera-knowledge/test-content
Verify Cleanup: Call MCP tool execute with { command: "stores" }
After running all tests, report results in this format:
| # | Test | Status |
|---|---|---|
| 1 | MCP Connection (help) | ? |
| 2 | List Stores (MCP) | ? |
| 3 | Create Store | ? |
| 4 | Store Info | ? |
| 5 | Index Store | ? |
| 6 | Search (MCP) | ? |
| 7 | Get Full Context | ? |
| 8 | /stores Command | ? |
| 9 | /search Command | ? |
| 10 | /suggest Command | ? |
| 11 | Delete Store | ? |
| 12 | Remove Test Content | ? |
| 13 | Verify Cleanup | ? |
Result: X/13 tests passed
If tests fail partway through, clean up manually:
Delete test store (if exists):
execute → { command: "store:delete", args: { store: "bk-test-store" } }
Remove test content directory:
rm -rf .bluera/bluera-knowledge/test-content