"Session" matching MCP servers:

Read visual bug reports from Feedbug in your AI coding agent: screenshot, console logs, failed network requests, session replay and the DOM context of the element the tester clicked. Trace the bug to its source file, comment and resolve without leaving the editor.

Verify AI agent communication with session types and formal proofs. 4 tools: parse protocols, verify messages, check safety properties, browse 20 stdlib templates.

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.

Enables LLMs to read existing PageSnap session packs and map locators to Playwright, Selenium, or Cypress without capturing or opening a browser.

Enables automated testing and demo video creation using Playwright, with login, session orchestration, narration, and video compilation.

Enables AI agents to perform real accessibility audits by controlling a browser, running axe-core scans, reviewing page structure, images, tab order, and WCAG 2.2 color contrast, all over MCP with local session logging.

Enables AI assistants to automate mobile app testing and development for iOS and Android through natural language interactions. Supports intelligent element identification, session management, automated test generation, and comprehensive device interactions including clicks, swipes, screenshots, and app management.

Provides Codex and other MCP clients a local web debugging server that coordinates a browser session, JavaScript debugger, bounded runtime evidence, and reproducible flow verification for vanilla HTML/JS projects.

Website testing MCP server built for AI agents: 63 Playwright tools with hard assertions, auto form-fill, persistent authenticated sessions, network mocking, and accessibility/SEO/GEO + Lighthouse audits.

Guides developers through disciplined Test-Driven Development cycles with session state management and phase transitions, ensuring test-first methodology.

Enables an agent to drive a real Ragnarok Online client session against a local rAthena server, allowing it to log in, walk, talk to NPCs, and fight in order to test server content end to end.

Enables AI assistants to configure and manage session-based REST and WebSocket mock servers for application development and testing. It allows for dynamic endpoint setup, request history inspection, and real-time WebSocket communication through natural language commands.

Adds persistent QA state to browser automation, enabling AI agents to maintain session-scoped artifacts and generate reports across multiple steps.

Enables Codex CLI to perform code reviews on uncommitted changes via an MCP tool, keeping review context separate from the main session.

An MCP server that enables reading and managing Zentao tasks, bugs, requirements, test cases, and test suites via the ZenTao 11.3 Legacy Session API. It integrates with MCP clients like Codex, Claude Desktop, and Cursor.

Enables mobile device management, app upload, automation session execution, and test result viewing through the Kobiton platform, integrated with AI coding assistants.

Validates a built HTML5 game against CrazyGames portal rules — build checks, an emulated SDK v3 session, and frame/layout audits — returning dense JSON lists of failures, warnings and rules it could not exercise instead of screenshots or ad-hoc Playwright scripts. It emulates the portal entirely in-process (no server or port) using the game's own Playwright/Chromium, with a small per-game scenario file driving gameplay steps.

Enables automated testing and development of Expo/React Native apps through session-based Expo dev server management and Maestro UI automation tools for tapping, text input, screenshots, and flow execution.

Local MCP server for Android and iOS mobile automation and performance telemetry, enabling device control (screenshot, tap, swipe, input, app launch) and metric collection (CPU, memory, launch time) via ADB, simctl, and WebDriverAgent with SQLite session history.

Enables auditing coding-agent claims against local execution traces to detect contradictions, exposing session audits, recent failures, and optional scope-alignment triage.