- 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.
Testgen Eval
An agent-eval harness that gates and judges testgen's generated test suites via MCP — deterministic checks plus an LLM-judge scorecard.
Mocking Agents MCP A2a
How to mock agents, MCP servers and A2A peers for production-grade agent development. Protocol surfaces verified against MCP 2026-07-28 and A2A v1.0 (August 2026).
Kubeshop
Kubeshop — independent third-party profile of a public API surface, by API Evangelist. Kubeshop is the company behind Testkube, an open-core, Kubernetes-native test orchestration…
Robotics Devkit
Reusable plugin marketplace and template for the code-to-simulation-to-real-robot development ladder, with MCP tools, test agents, and project memory.
Mcplab.dev
Website and documentation for MCP Lab and MCP Failure Lab
Blender MCP Ocarina
Automate and snapshot-test Blender through MCP with Ocarina. No LLM.
Awesome MCP Testing
A curated list of tools for testing, evaluating, validating and debugging MCP (Model Context Protocol) servers: inspectors, conformance suites, eval harnesses, test libraries, sca…
Uat
AI-native test engine for browser, API & MCP testing — 46 tools over Model Context Protocol. Built with Playwright + Bun.
Badge
GitHub Action that turns a live MCP (Model Context Protocol) conformance check into a self-contained SVG status badge for your README — no badge service, no external host. initial…
Webmcp Optimized
Refactored fork of jasonjmcghee/WebMCP, the bridge that lets a website act as an MCP server. Monolith split into focused modules, 693 to 368 line deduplication, 25 tests where ups…
Sim
MCP server for managing iOS Simulator and Android Emulator lifecycle on a remote macOS host. Agent-driven emulators without the idle footprint.
Agent Regress
MCP server for regression-testing AI agents — deterministic checks (regex, exact-match, JSON schema, exit code), zero API keys required.
Devt
Zero-dependency multi-agent development workflow plugin for Claude Code
Coverwise MCP
Pairwise / t-wise combinatorial coverage for AI-written tests — check what a suite misses, generate the minimum matrix, extend it without rewriting. A Claude Code plugin and a sta…
Lims MCP
Locator Intelligence MCP Server — AI-powered locator generation, self-healing, and Playwright framework sync for Cursor
Windtunnel
Unittest for tool-using LLM agents: reproducible scenarios scoring outcome, trajectory, constraints, and robustness.
Duckdb MCP Ocarina
Clone-and-run data tests for DuckDB through MCP, driven by Ocarina. No LLM.
Flightcheck
Tries to break your MCP server before your users do. Runtime checks with spec citations, made for CI.
Millipede
AI agent perceives, drives & verifies a live Flutter app via MCP — in-app probe + MCP CLI
Trust Check
Runs the full MCP trust & safety trilogy — mcp-doctor + mcp-fuzz + mcp-reality-check — as one GitHub Action for CI, or one Python package (GuardedSession) for a live agent session…
Stdio Purity
Fail CI when an MCP stdio server writes any non-JSON-RPC record to stdout during startup, probing, or cleanup.
Github Copilot Qa Use Cases
GitHub Copilot - QA use cases: unit, integration, Playwright E2E, MCP, Actions, and specialized QA agents.
mohamed-khairy-5i/tossinbox
5i/tap/tossinbox`.
Gonemaster
Domain delegation testing - Read-only mirror of https://codeberg.org/pawal/gonemaster
Testlease
Stop parallel tests from fighting over shared test accounts and environments. Exclusive, expiring leases with evidence.
Godot Verify Plugin
Validation-driven AI development harness for Godot 4.x (Claude Code plugin): headless SceneTree matrix oracle + live MCP game channel.
TestableUIKit
iOS UI component self-reporting HTTP IPC testing framework
Pdverify
Render Pure Data patches headless and verify what they actually sound like — the audio-verification piece missing from Pd LLM harnesses.
Qa Factory Core
Local-first AI-readable QA issue and run store with an optional MCP adapter.
Android Driver
Drive an Android emulator as a deterministic test harness, from Claude Code. MCP server with snapshots, a compact screen index, and evidence-collecting assertions.
Heavnz0r Crashlab
A fault laboratory for agent workflows: deterministic MCP tool failures, effect invariants, counterexamples, and action replay.
passmcp
Test any Model Context Protocol server and find out, in plain language, whether it is ready for your agents — and exactly what to fix if it is not.
Kosher
Kosher updates BDD for the AI era.
BugForge
server that converts test failures into Jira-ready defect reports — inside any MCP Client, no LLM API key needed.
Kaattaallaa Sketch.github.io
ProofRail: MCP server testing, evaluation and compatibility preflight for AI agents; MCP, A2A, OpenAPI and x402 discovery.
Tool Schema Fuzzer
Generate adversarial test cases from an MCP tools/list: valid-minimal, missing-required, wrong-type, extra-field, boundary, enum-violation. Each carries an expected accept/reject…
Proba
The QA workbench for the agent era: drive web/API/DB through MCP and own the tests you get back (Gherkin <-> JSON <-> Playwright). Replay evidence, failure clips, self-healing, cr…
Unified MCP Control Plane
Policy-gated MCP control plane with OAuth 2.1, provider adapters, risk classification, credential redaction, and Node/Cloudflare runtimes.
Autonomous Security Lab Assistant
Safe-by-default MCP-style assistant for scoped security lab workflows.
Fixture MCP
MCP server for stateful API testing by AI agents.
Runproof
Privacy-first local evidence compiler for AI tool runs — deterministic fixtures, redaction, fingerprints, SARIF, and JUnit.
Embodied Ha MCP Lab
Developer and audit add-on for exercising Embodied HA MCP tools
Page MCP
One <script> turns your web UI accessible to any agents for dev, test, debug by exposing curated tools as WebMCP
Test Automator
LLM-powered testing automation MCP server for unit, integration, API, and E2E tests with Windows support for 90K+ line codebases
Coverage Report
An MCP tool to manage python tests coverage
Make Testkit
Test Make.com (Integromat) scenarios offline — execution engine + MCP server + Claude Code plugin
Tool Call Replay Harness
Offline replay and assertion harness for AI agent tool-call transcripts, fixtures, retries, budgets, JUnit reports, and CI gates.
Accessibility Engine
AI-first accessibility testing: augments Playwright with contextual AI quality judgments grounded in captured evidence. Local-first, no API key.
Tool Semantics
Behavioral compatibility testing for MCP tools and AI-agent interfaces know when a change breaks the agent, not just the schema.
E2H
Evidence-to-Harness toolkit for reproducible AI-agent evaluations, observable evidence, deterministic replay, and verifiable releases.