Testing

18,508 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

mockmcp

1657

K-Cupples/mockmcp

MCP server Claude CodeCodexCursor +2

Hosted MCP endpoint with realistic fake data for prototyping agents. 12 tools, no setup. Remote server at mockmcp.io.

not rated 0 4mo ago A tokens not measured original MIT

mcp

1658

LambdaTest/mcp-server-guide

MCP server Claude CodeCodexCursor +2

Agentic testing: HyperExecute jobs, test failure triage, SmartUI visual diffs, a11y audits. Remote server at mcp.lambdatest.com.

not rated 0 1mo ago A tokens not measured

hwcontract

1659

MohibShaikh/hwcontract

Skill Claude CodeCodex

Use when firmware has timing or level requirements you can measure against a spec: pulse widths on a WS2812/NeoPixel strip, DShot ESC, servo, I2C, NEC IR, DS18B20/DHT sensor, A4988/DRV8825 stepper, PWM fan, HC-SR04, when a board prints a boot log over serial (ESP32, ESP8266, Zephyr, MicroPython, u-boot, Raspberry Pi…

not rated 0 19d ago A 149 tokens original MIT

octoperf

1660

OctoPerf/octoperf-claude-plugins

Plugin Claude Code

Bundles 20 skills, 1 MCP server · 1,589 tokens together

OctoPerf load-testing platform — connects to the hosted MCP server (HTTP + OAuth 2.1 PKCE + DCR) and bundles workflow skills (auto-correlation, validation triage, scenario diagnosis, bench reports, real-browser probe, scheduling).

not rated 0 5d ago A tokens not measured original Apache-2.0

perf-mcp

1661

Perf-Technology/perf-mcp

MCP server Claude CodeCodexCursor +2

Fact-check and fix AI outputs. Hallucination detection, schema validation, auto-repair. Runs locally from the perf-mcp npm package. Needs 1 environment variable to run.

not rated 0 6mo ago A tokens not measured original MIT

repo-test-architect

1662

RepoAssay/repo-test-architect

MCP server Claude CodeCodexCursor +2

Audit-first test strategy MCP server for repository-native test planning. Runs locally from the repo-test-architect npm package.

not rated 0 2d ago A tokens not measured original MIT

devicecloud

1663

RubenGlez/devicecloud-mcp

MCP server Claude CodeCodexCursor +2

Triage failing DeviceCloud Maestro test runs: fail reasons, screenshots, flaky-flow analytics. Runs locally from the devicecloud-mcp npm package. Needs 1 environment variable to run.

not rated 0 1mo ago A tokens not measured original MIT

agent-eval

1664

RudrenduPaul/agent-eval

MCP server Claude CodeCodexCursor +2

Statistical regression testing for LLM agents. Get a p-value on whether behavior actually shifted between versions, not just whether one run looked different. Apache 2.0, self-hostable, no SaaS dependency -- a Promptfoo alternative for the statistical testing gap threshold-based eval tools don't cover. Runs locally…

not rated 0 4d ago A tokens not measured original Apache-2.0

slop-eval

1665

RudrenduPaul/slop-eval

MCP server Claude CodeCodexCursor +2

Scores AI-generated UI for genericness ("slop") using an Anthropic LLM-judge rubric, with a --json mode for CI/agent quality gates and a documented programmatic API (scorecomposite, ScoreInput, LLMJudgeSource) for in-process use by agent frameworks. Runs locally from the slop-eval-cli Python package.

not rated 0 2d ago A tokens not measured original Apache-2.0

swing-ui-testing

1666

TinusJ/swing-mcp

Skill Claude CodeCodex

Uses Swing MCP to test and verify Java Swing application behavior. Use when writing or executing UI test scenarios against Swing apps - filling forms, verifying tables and trees, exercising menus and dialogs, testing keyboard navigation, and visually verifying results.

not rated 0 1mo ago A 51 tokens original MIT

mcp

1667

WCAG-Compliance/wcagc-mcp

MCP server Claude CodeCodexCursor +2

Deterministic axe-core accessibility scans (WCAG 2.1 AA, EN 301 549, PDF/UA) via your account. Runs locally from the @wcagc/mcp npm package. Needs 2 environment variables to run.

not rated 0 5d ago A tokens not measured original MIT

koda

1668

aabxtract/koda

MCP server Claude CodeCodexCursor +2

Verification and memory layer for coding-agent workflows. Runs locally from the koda-verify npm package.

not rated 0 12d ago A tokens not measured original MIT

forgejudge

1669

ahmedEid1/forgejudge

MCP server Claude CodeCodexCursor +2

Open, always-on leaderboard + CI gate for autonomous coding agents — every patch sandboxed, every run traced, every regression fails the build. Runs locally from the forgejudge Python package.

not rated 0 21d ago A tokens not measured original MIT

mcp-failure-lab

1670

anilloutombam/mcp-failure-lab

MCP server Claude CodeCodexCursor +2

A chaos-engineering and resilience-testing toolkit for Model Context Protocol servers. Runs locally from the mcp-failure-lab npm package.

not rated 0 3d ago A tokens not measured original MIT

account-pool-mcp

1671

ankitsxchdeva/account-pool-mcp

MCP server Claude CodeCodexCursor +2

Exclusive, crash-safe leases on a pool of test accounts for parallel agent QA runs. Runs locally from the account-pool-mcp npm package. Needs 4 environment variables to run.

not rated 0 yesterday A tokens not measured original MIT

twothumbs

1672

asselwan/twothumbs-mcp

Plugin Claude Code

Bundles 1 MCP server

Verify what your AI agent actually did, not what it says it did. Connects to the hosted TwoThumbs MCP server (runverdict, listsurfaces, redeemcode) over Streamable HTTP.

not rated 0 1mo ago A tokens not measured

agenttrust

1673

assister-xyz/quality-oracle

MCP server Claude CodeCodexCursor +2

AgentTrust MCP Server — verify AI agent and MCP server quality from your IDE. Runs locally from the mcp-agenttrust Python package. Needs 3 environment variables to run.

not rated 0 4mo ago A tokens not measured original MIT

noisefloor

1674

beepboop2025/noisefloor

MCP server Claude CodeCodexCursor +2

Is this number real, or is it noise? Peek-safe A/B tests, change detection and honest forecasts. Zero dependencies. Runs locally from the noisefloor Python package.

not rated 0 21d ago A tokens not measured original MIT

beforeusersdo-qa

1675

bhuman-ai/QAbro

Skill Codex

Route and run BeforeUsersDo QA through its MCP tools. Use when a user asks to test, QA, review, or get feedback on a website, app, feature, preview, or user flow; asks for AI QA, a personal self-review, a real human tester, QA status, video, transcript, findings, or a completed BeforeUsersDo report.

not rated 0 21d ago A 79 tokens

artifactguard

1676

blackcow4234-lab/blackcow4234

MCP server Claude CodeCodexCursor +2

Signed PASS/WARN/FAIL QA receipts for AI-generated JSON, ZIP, PDF, and DOCX deliverables. Remote server at analytical-gratefulne--artifactguard.apify.actor.

not rated 0 1mo ago A tokens not measured

puzzletide-agent-evals

1677

Caravaca-Labs/puzzletide-cli

Skill Claude CodeCodex

Use this skill when the user wants verifiable reasoning tasks to benchmark or test an LLM or agent — reproducible puzzle task sets (sudoku, word search) with objective, by-construction grading. No answer key to trust: answers are verified against the rules and the grid.

not rated 0 1mo ago A 65 tokens original MIT

ghost-inspector-mcp

1678

charliemtnez/ghost-inspector-mcp

MCP server Claude CodeCodexCursor +2

Analyze, validate and safely update Ghost Inspector end-to-end browser tests. Runs locally from the ghost-inspector-mcp npm package. Needs 4 environment variables to run.

not rated 0 1mo ago A tokens not measured original MIT

mcp-eval-runner

1679

dbsectrainer/mcp-eval-runner

MCP server Claude CodeCodexCursor +2

A standardized testing harness for MCP servers and agent workflows. Runs locally from the mcp-eval-runner npm package. Needs 1 environment variable to run.

not rated 0 3mo ago A tokens not measured original MIT

qtm4j

1680

denis-platonov/qtm4j-mcp-server

MCP server Claude CodeCodexCursor +2

MCP server for QMetry Test Management for Jira (QTM4J) Open API. Runs locally from the @denis-platonov/qtm4j-mcp-server npm package. Needs 4 environment variables to run.

not rated 0 4mo ago A tokens not measured original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: