- Conduid
- Marketplace
- #testing
MCP servers tagged testing
472 live MCP servers tagged "testing", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with testing.
Agent Full Pro
A practical Flutter/App agent framework: Simple vs Complex workflow, evidence-first delivery, MCP optional with Android Studio fallback.
Sideeye
A deterministic skeptic for the coding loop: breaks your software's world and brings back the smallest reproducible counterexample. Sideeye doesn't believe it.
Faultbench
Fake, stateful worlds with fault injection for testing tool-using AI agents — over MCP, asserted from pytest.
Qajev
Test your website the way a person uses it: plain-language goals, verdicts from the page. A CLI and an MCP server for people and AI agents.
Playwright MCP Server
This repository documents hands-on experience working with Playwright Test Agents through MCP.
Harness
In-memory testing toolkit for MCP servers in TypeScript - supertest for MCP
Aegis Guardrails
Deterministic governance and guardrails for autonomous AI coding agents. Features AST verification, evidence-based rule execution, and native MCP support for Antigravity and Claud…
Mcpunit
The testing framework for MCP servers.
Mockifyer
Record/replay HTTP mocking for fetch & axios — React Native/Expo-first, with scenarios, a dashboard, and an MCP server for AI assistants.
QA AI STLC
Open-source, model-agnostic QA framework that runs inside Claude Code and Codex
Checkpoint
The release gate for AI agents — run your real agent N times against stateful twins and ship only when the confidence interval says so.
Microgpt Agent SDK
🧠 Build AI agents with advanced memory and multi-agent orchestration using this production-ready TypeScript SDK. Test before you deploy.
Test Framework
A pytest plugin for testing MCP (Model Context Protocol) servers
Alethia MCP
MCP bridge for Alethia — the zero-IPC E2E testing framework built for AI agents
Pickforge
Playwright, for native apps. Native-app + Android-emulator automation for AI coding agents (CLI + MCP).
Qikly
Generates a test suite from acceptance criteria, then converges code against it with an agent that never sees those criteria.
Game Bridge MCP
Port-addressable MCP bridge for driving running games over a debug HTTP surface: launches instances and picks their ports, discovers each game's tool list at runtime, drives many…
Policy Testkit
CI-first policy and security testkit for MCP servers, manifests, metadata, and source artifacts.
Accessibility Suite
Unified monorepo for accessibility testing, evidence generation, and WCAG compliance tooling
Msw Skill
AI agent skill for MSW 2.0 — 20 rules: handler design, REST/GraphQL, test patterns. Works with Claude Code, Cursor, Codex, Windsurf.
Evidence Gate Dogfood
Cross-repository dogfood fixture for MCP Evidence Gate Action integration evidence.
Vidqa
pip install vidqa-cli — local, deterministic video QA CLI + MCP for tests, CI, and agents: 28 commands — frame timing, golden-frame diff, failure auto-locate, on-screen text index…
Pinchy
Poke GNOME apps from the command line: a private headless session you can screenshot, click and type into - for tests, scripts and coding agents. MCP server included.
Blop MCP
MCP-native release confidence control plane for web apps
A11ied
A library, CLI tool, and MCP server for automated and scripted accessibility testing using VoiceOver (macOS) and NVDA (Windows)
SceneScout
🔭 Exploratory UI testing for AI coding agents, over MCP. Works with Claude Code, Cursor, VS Code, Codex, Gemini CLI and more: a structured view of a running web app, always-on ora…
Dsh Godot Game Studio
Seven bounded Godot 4 MCP tools for DeepSeek Harness: audit, test, simulate, validate, and release
Flightdeck
Deterministic testing and replay for MCP servers.
Skill Test Execution
Test execution skill — unit, integration, E2E tests, coverage, and failure analysis via mcp-test-runner
Traceplay
VCR-style regression harness for AI agents: record trajectories once, replay offline with zero tokens, and assert behavior in CI.
Mechanics
Behavior-spec system for apps: full-spec user stories, coverage-audited manifests, e2e-linked verification waves. CLI + MCP + Claude Code skills + forkable template.
Hl7fhirgen
Generate, validate, and explain FHIR resources against any StructureDefinition profile — plus an NPHIES pack for pre-submission claim checking, an MCP server & Claude Code plugin,…
Layoutlint
Layout checks and screenshots for JSX/HTML + Tailwind in milliseconds, no browser — verified against Chromium. Eyes for AI coding agents.
Zeruxjs
A FullStack Framework
Swarmbreaker
Load and chaos testing for AI agent orchestration plumbing: adversarial mock model endpoint + mock MCP tool fabric, knee detection with CIs, honest confidence labels.
Kadeep CLI
KaDeep Studios CLI and releasegate: AI end-to-end testing from your terminal, CI/CD and coding agents (MCP). Run tests on web, mobile and desktop and get a go / no-go for every re…
Migration Test Framework
Migration test framework
StoryForge Agent
Plan → search → revise thin results → brief → HITL → shoot-ready script. | S, t, r, e | Tracked repository files: 22; Python modules: 17
Testmu Browser Agent Public
AI-native browser automation CLI and MCP server for Chrome. 90+ commands. Works with Claude Code, Cursor, Copilot, and 6 more.
Shadow Mirror
Referential introspection for test planning and coverage mapping — Claude Code plugin + methodology (SM-0..SM-6).
Agent Reliability Toolkit
Test AI agents repeatedly, measure reliability, classify failures, and catch regressions before production.
Imstage
Synthetic conversations for non-commercial testing, learning and evaluation. Generic chat rendering with visible fictional-content labels.
Master Tester
Local web UI to connect, inspect and test any MCP server — stdio, Streamable HTTP & SSE, with auth prompts, schema-driven tool forms, elicitation, linting and a live JSON-RPC log.
Report Bridge
Import test results into a shared IR and preview Cucumber-style, Allure-like, and Extent-like reports.
Google Flights MCP Server
This project provides a local MCP server that allows you to: Search flights via Google Flights (SerpAPI), including: One-way, Round-trip, Multi-city itineraries Perform bookings…
Faultline
Failure-mode evaluation for MCP agents. Inject faults, observe trajectory, grade resilience with evidence. 5-layer grading, 18 fault types, replay.
Vitest MCP
Vitest harness and matchers for testing MCP servers — in-memory transport, real protocol path, millisecond tests.
Fieldtwin
Local, stateful twins of the Jobber and QuickBooks Online APIs. Build and test integrations and AI agents against a believable fake business, with resets, rewind, controllable tim…
Dev Kit
Complete testing & debugging toolkit for MCP (Model Context Protocol) servers
Mcptest
Go testing library for MCP servers — in-memory client, assertions, spy, and sampling mock