"MCP servers that integrate with GPT" matching MCP servers:

Enables coding agents to request, track, and verify independent cross-model reviews with structured findings, attachment hashes, and provenance receipts via Chrome Bridge, Codex, or Responses transports.

Provides a read-only MCP bridge that lets Claude Web inspect workspace files, git state, and recorded test results while Codex remains the sole executor of changes.

Provides a framework for running multiple MCP servers using FastAPI, stdio, and streamable-http transports, with an echo tool for testing and integration with MCP Inspector.

Browser automation that bypasses anti-bot systems and handles web-scraping with CDP Mode.

VAST validation MCP server that checks ad tags against IAB VAST specifications, returning structured JSON with rule IDs, XPath locations, and spec references.

A universal MCP server that dynamically generates and simulates actions for any query, maintaining state between sessions.

MCP bridge that lets any MCP client drive the Alethia runtime for agent-native E2E testing. It provides a per-step policy gate that blocks destructive actions with a cryptographic audit trail.

An MCP server that manages a pool of test accounts, leasing them out one at a time to prevent concurrent session collisions, with automatic reclamation of expired leases.

An automated testing MCP server that converts test cases into a fixed JSON format, runs them case-by-case, and provides a visual report with review support for cases that cannot be automatically judged.

A stdio MCP server that audits other MCP servers by linting their tool schemas and calling tools with malformed inputs to produce a 0–100 conformance score and Markdown report.

Checks a repository's own guardrails and fails any that are present but have stopped refusing anything. Three read-only tools: installation status, per-step verification that issues a receipt, and a tail of the append-only ledger recording every question and answer.

AI-optimized Vitest interface that provides structured test output, visual debugging context, and intelligent coverage analysis for more effective AI assistance with testing.

MCP server that aggregates test failures, cross-references flakiness history, and outputs a release readiness verdict.

MCP server that lets coding agents test AI agents. Create YAML test cases, snapshot golden baselines, check for regressions, and generate visual reports all from inside Claude Code or any MCP-compatible tool. Works with LangGraph, CrewAI, OpenAI, Claude, Mistral, and any HTTP API.

A local MCP server that exposes a web accessibility knowledge base with WCAG 2.2 criteria and ABNT NBR 17225 correlations, enabling AI agents to retrieve criterion details, search by keyword, and generate manual test routines.

An MCP server that provides tools to interact with the JSONPlaceholder fake REST API for testing and prototyping, supporting CRUD operations on posts, comments, todos, and users.

An MCP server that lets AI agents run PHP unit and integration tests inside Docker containers without local PHP or Composer.

MCP server that integrates with Testmo to let AI assistants read projects, runs, results, and test cases, and create or update runs, results, and cases via natural language.

Enables auditing any public website, returning a scored plain-English report that flags issues costing customers, covering speed, phone experience, search visibility, contact options, writing quality, and modernity.

Peeko is a read-only MCP server that provides Claude with screenshots of iOS Simulators, Android emulators, or physical Android devices.