"author:clauxel" matching MCP servers:

Catch Gemini model upgrade regressions before they reach customers by running evals, comparing outputs, detecting regressions, and exporting audit receipts.

A paid remote MCP release gate for Kiro projects that enables release policy checks, evidence collection, owner signoff, and CI-friendly approval receipts.

A hosted remote MCP for A2A failure replay, providing tools to replay failures, classify agent errors, suggest retry plans, issue receipts, and export failure logs.

A paid remote MCP server for checking extension compatibility and generating structured receipts, audit logs, and reviewer-ready evidence.

Replay safety evals before agent releases move forward. A paid remote MCP for AI agent safety replay checks, policy gates, eval receipts, control-fix suggestions, and release evidence exports.

A paid remote MCP server for AI SDK eval dashboards, offering structured tools for evaluation gates, trace failure summaries, version comparisons, and audit receipts with token-based access.

Paid remote MCP for Skybridge that packages apps, validates schemas, runs compatibility tests, and exports manifests with audit-ready JSON evidence.

Prove your SRE agent can resolve incidents before production by replaying synthetic incidents and scoring agent performance via MCP tools.

Enables automated HTML export quality assurance with structured receipts, audit logs, and reviewer-ready evidence through a paid remote MCP server.

A paid remote MCP server for OpenAI Codex harness, offering structured JSON tools for coding task planning, safe command suggestions, test verdict recording, and run history.

Enables spec-driven development acceptance gate with structured receipts, audit logs, and reviewer-ready evidence.

Paid hosted MCP endpoint for AI SDK benchmark dashboard, providing tools for running benchmarks, comparing model scores, reading reports, and issuing receipts.

Detects brittle Playwright selectors and provides healing suggestions, action receipts, human approvals, and failure exports.

Enables AI agents to test Unity scenes and return review-ready receipts via a hosted remote MCP with tools for playmode checks and method invocation.