MicroShift Test Analyzer

Analyzes MicroShift test failures from Google Sheets to correlate them with specific MicroShift versions.

A Python-based MCP (Model Context Protocol) server that analyzes MicroShift test failures from Google Sheets, providing specialized tools for correlating test failures with MicroShift versions.

- Failed Pipelines by Version: Get failed testing pipelines grouped by MicroShift version
- Failure Summary: Get aggregate statistics of test failures across all versions
- Pipeline Failure Trends: Analyze failure trends for specific testing pipelines over time
- Search Failure Reasons: Search for specific failure reasons across all tests
- Version Comparison: Compare test results between different MicroShift versions
- Real-time Data: Fetches data directly from Google Sheets
- Go toGoogle Cloud Console
- Create a new project or select an existing one
- Enable the Google Sheets API
- Create a service account:

GOOGLE_CLIENT_EMAIL=your-service-account@your-project.iam.gserviceaccount.com GOOGLE_PRIVATE_KEY="-----BEGIN PRIVATE KEY-----\nYour private key content\n-----END PRIVATE KEY-----\n"

This server follows the officialMCP Python SDKpattern usingFastMCP. It can be used with any MCP-compatible client like Claude for Desktop.

{ "mcpServers": { "microshift-test-analyzer": { "command": "python", "args": ["/absolute/path/to/mcp-test-scenarios-server/server.py"], "cwd": "/absolute/path/to/mcp-test-scenarios-server" } } }

Once connected to Claude for Desktop, you can ask questions like:

- "What testing pipelines failed for MicroShift version 4.18.0?"
- "Show me all failures related to 'ssh connection failed'"
- "Compare test results between version 4.18.0 and 4.17.0"
- "What are the failure trends for the rpm upgrade pipeline?"
- "Give me a summary of all test failures grouped by reason"

- Ensure yourGOOGLE_CLIENT_EMAILandGOOGLE_PRIVATE_KEYenvironment variables are set correctly
- Verify the service account has access to the Google Sheet
- Check that the Google Sheets API is enabled in your Google Cloud project
- Make sure the private key format is correct (including \n characters)

- Verify that your spreadsheet follows the expected column structure
- Ensure pipeline data is formatted with proper line breaks separating different components
- Check that status values are one of: SUCCESS, FAILURE, FAILED, PASS, PASSED

- Make sure the server script path in your MCP configuration is correct
- Verify that all required Python dependencies are installed
- Check that the Google Sheets ID in the server code matches your actual spreadsheet

- "No data available": The spreadsheet is empty or the parsing failed
- "Invalid credentials": Service account authentication failed
- "Permission denied": Service account lacks access to the spreadsheet
- "Column index out of range": Spreadsheet structure doesn't match expected format

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Agent Droid Bridge gives AI agents programmatic control over Android devices and emulators via ADB, exposed as an MCP server.

Control Android devices using the Android Debug Bridge (ADB).

A hosted MCP server for generating fake data using faker-go

Access and manage Grafana resources, including dashboards, datasources, Prometheus, Loki, and alerting.

A JSON diff tool to compare two JSON strings.

Reads Allure test reports and returns them in LLM-friendly formats for better test analysis and insights.

Security testing MCP server with 51 tools for penetration testing, network forensics, memory analysis, and vulnerability assessment.

Fact-check and fix AI outputs — hallucination detection, schema validation, and auto-repair.

Control your Android phone using ADB commands. Requires ADB tools and an Android device with USB debugging enabled.

Expose Prometheus monitoring tools to an LLM for querying and analysis.