About geminiupgradeqa-mcp
A remote MCP service for AI platform teams, prompt owners, QA leads, and release engineers to evaluate Gemini upgrades and catch prompt regressions. It compares outputs, detects regressions, applies blocking rules, and exports evaluation receipts.
Key features
- 01Run Gemini upgrade evaluations
- 02Compare prompt outputs
- 03Detect model regressions
- 04Apply blocking rules
- 05Export evaluation receipts
Use cases
- 01Check Gemini upgrades before release
- 02Review changes between prompt outputs
- 03Block releases on detected regressions
MCP support
Exposes remote MCP tools for running evaluations, comparing outputs, detecting regressions, issuing upgrade receipts, and exporting evaluation audits.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://geminiupgradeqa.clauxel.com/mcpclaude mcp add --transport http com-clauxel-geminiupgradeqa-geminiupgradeqa https://geminiupgradeqa.clauxel.com/mcp{"mcpServers":{"com-clauxel-geminiupgradeqa-geminiupgradeqa":{"type":"http","url":"https://geminiupgradeqa.clauxel.com/mcp"}}}Open in Cursor{"servers":{"com-clauxel-geminiupgradeqa-geminiupgradeqa":{"type":"http","url":"https://geminiupgradeqa.clauxel.com/mcp"}}}Open in VS Code{"mcpServers":{"com-clauxel-geminiupgradeqa-geminiupgradeqa":{"type":"http","url":"https://geminiupgradeqa.clauxel.com/mcp"}}}{"mcpServers":{"com-clauxel-geminiupgradeqa-geminiupgradeqa":{"serverUrl":"https://geminiupgradeqa.clauxel.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://geminiupgradeqa.clauxel.com/mcpAuth requiredTools
Details
From the project READMEGemini Upgrade QA MCP
Catch Gemini model upgrade regressions before they reach customers.
Gemini Upgrade QA is a paid remote MCP for Gemini upgrade evals, prompt regression checks, model output diffs, blocking rules, and eval receipts.
This is a public documentation project for Gemini Upgrade QA MCP. The structure is modeled after the public documentation pattern used by MiroFish: a short front door, a clear reading order, practical guides, reference pages, and public-safe architecture notes.
Start Here
- Website: https://geminiupgradeqa.clauxel.com/?utm_source=github&utm_medium=documentation&utm_campaign=geminiupgradeqa_public_docs&utm_content=readme_primary_home
- Pricing: https://geminiupgradeqa.clauxel.com/pricing/?utm_source=github&utm_medium=documentation&utm_campaign=geminiupgradeqa_public_docs&utm_content=readme_pricing
- Checkout: https://geminiupgradeqa.clauxel.com/checkout/?utm_source=github&utm_medium=documentation&utm_campaign=geminiupgradeqa_public_docs&utm_content=readme_checkout
- Support: [email protected]
Remote MCP
- Endpoint: https://geminiupgradeqa.clauxel.com/mcp
- Server card: https://geminiupgradeqa.clauxel.com/server-card.json
- Registry name:
com.clauxel.geminiupgradeqa/geminiupgradeqa-mcp - Tools:
run_gemini_upgrade_eval,compare_prompt_outputs,detect_model_regression,issue_upgrade_receipt,export_eval_audit
Reading Order
Audience
AI platform teams, prompt owners, QA leads, and release engineers.
Capabilities
- upgrade eval runner
- prompt output comparison
- regression detection
- blocking rules
- eval receipt export
Public-Safe Boundary
This repository does not contain production source code, credentials, payment configuration, Cloudflare configuration, customer records, private analytics, or local machine paths.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.