Skip to content
Agentmart
Submit a tool

AI agent tools for testing

In this catalog, a testing tool is one that writes, runs or maintains automated tests (unit, integration, end-to-end). Our enrichment pass tags 476 listings with it: 101 MCP servers, 245 agent skills, 96 plugins, 1 agent framework, 32 AI agents and 1 no-code agent builder. By listing rank, the top MCP server is Oh My Posh Validator, the top agent skill is cloud and the top plugin is BAML v0. 33 of the 476 are published by the vendor behind the product, and 387 were active in the last 30 days. 7 of the 101 MCP servers run only as remote servers, with nothing to install locally. Each entry below links to its listing page, with grades, install commands and sources.

Updated Oct 26, 2026 · Built from catalog data; how we rank and grade

What the job is

Tagged listings
476
By type
101 MCP servers, 245 agent skills, 96 plugins, 1 agent framework, 32 AI agents and 1 no-code agent builder
Published by the vendor
33 of 476
Active in the last 30 days
387 of 476
Open source
393 of 476
MCP servers that run only remotely
7 of 101
Hosts named by the MCP servers
Claude Code (95), Cursor (95), VS Code (95)

Building blocks by type

The top entries of each type, by listing rank. Open a listing for its install command, grades and sources.

MCP servers 101 tagged

  1. 1
    Oh My Posh Validator

    ohmyposh.devOfficial

    Validate oh-my-posh configurations and segment snippets against the official schema.

    • Published by the vendor
    • Most GitHub stars here (23,644)
    • Remote server, no local install

    ★ 23.6KLast active Oct 20, 2026Remote (HTTP)Claude Code, VS Code, Cursor, Windsurf

  2. 2
    Keploy

    keploy

    End-to-end API testing — generate and run tests from OpenAPI, curl, Postman, or real user traffic.

    • 18.7K GitHub stars
    • Remote server, no local install
    • Active in the last 30 days

    ★ 18.7KLast active Oct 24, 2026Remote (HTTP)Claude Code, VS Code, Cursor, Windsurf

  3. 3
    e2e

    tester-army

    Open live web and mobile app sessions from an e2e project to inspect the app and try locators.

    • 11.8K GitHub stars
    • Active in the last 30 days
    • Open source (Apache-2.0)

    ★ 11.8KLast active Oct 23, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2

  4. 4
    Unity MCP

    shiranui-isuzu.dev

    Unity Editor automation for AI agents: scenes, prefabs, assets, shaders, Timeline, tests, builds.

    • Active in the last 30 days
    • Open source (MIT)

    ★ 335Last active Oct 8, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2

  5. 5
    shaft-mcp

    ShaftHQ

    SHAFT browser automation, capture, and offline deterministic failure diagnosis

    • Active in the last 30 days
    • Open source (MIT)

    ★ 417Last active Oct 24, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2

Search MCP servers for testing → All connectors

Agent skills 245 tagged

  1. 1
    cloud

    browser-use

    Documentation reference for using Browser Use Cloud — the hosted API and SDK for browser automation.

    • Repository has 119K stars
    • Active in the last 30 days
    • Open source (MIT)

    ★ 119KLast active Oct 17, 2026Claude Code, Claude apps, Codex, Cursor +6

  2. 2
    rea-analysis-optimization

    morluto

    Optimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence.

    • Largest repository here (377,435 stars)
    • Active in the last 30 days
    • Open source (MIT)

    ★ 377.4KLast active Oct 18, 2026Claude Code, Claude apps, Codex, Cursor +6

  3. 3
    setup-pre-commit

    mattpocock

    Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo.

    • Repository has 302.4K stars
    • Active in the last 30 days
    • Open source (MIT)

    ★ 302.4KLast active Oct 4, 2026Claude Code, Claude apps, Codex, Cursor +6

  4. 4
    e2e-cucumber-playwright

    langgenius

    Use when writing, changing, or reviewing Cucumber and Playwright tests under `e2e/`, including feature files, step definitions, support code, scenario tags…

    • Repository has 159.4K stars
    • Active in the last 30 days

    ★ 159.4KLast active Oct 23, 2026Claude Code, Claude apps, Codex, Cursor +6

  5. 5
    dogfood

    vercel-labsOfficial

    Systematically explore and test a web application to find bugs, UX issues, and other problems.

    • Published by the vendor
    • Repository has 44.5K stars
    • Active in the last 30 days

    ★ 44.5KLast active Oct 22, 2026Claude Code, Claude apps, Codex, Cursor +6

Search agent skills for testing → All skills

Plugins 96 tagged

  1. 1
    BAML v0

    Boundary

    BAML v0 is a DSL for AI applications.

    • Most GitHub stars here (9,431)
    • Active in the last 30 days
    • Open source (Apache-2.0)

    ★ 9.4KLast active Oct 24, 2026VS Code, Cursor, Windsurf, VSCodium

  2. 2
    ChatGPT - Genie AI

    genieai

    Your best AI pair programmer.

    • 1.3K GitHub stars
    • Active in the last 30 days
    • Open source (ISC)

    ★ 1.3KLast active Oct 8, 2026VS Code, Cursor, Windsurf, VSCodium

  3. 3
    Power User for dbt

    Altimate Inc.

    Makes VS Code work seamlessly with dbt core and dbt cloud: auto-complete, preview, column lineage, AI docs generation, health checks, cost estimation etc

    • Active in the last 30 days
    • Open source (MIT)

    ★ 586Last active Oct 23, 2026VS Code, Cursor, Windsurf, VSCodium

  4. 4
    twinny - AI Code Completion and Chat

    twinnydotdev

    AI code completion, chat, inline edit and code review on models you run.

    • 3.7K GitHub stars
    • Active in the last 30 days
    • Open source (MIT)

    ★ 3.7KLast active Oct 16, 2026VS Code, Cursor, Windsurf, VSCodium

Search plugins for testing → All plugins

Agent frameworks 1 tagged

  1. 1
    judge0

    judge0

    Open-source online code execution system that runs submitted code in a sandbox behind an HTTP JSON API.

    • 4.5K GitHub stars
    • Active in the last 30 days
    • Open source (GPL-3.0)

    ★ 4.5K↓ 174/wkLast active Oct 18, 2026

Search agent frameworks for testing → All harnesses & sdks

AI agents 32 tagged

  1. 1
    Strix

    Strix

    Open-source autonomous pentesting agents that run your app, find vulnerabilities and validate them with working proofs of concept.

    • 71.6K GitHub stars
    • Active in the last 30 days
    • Open source (Apache-2.0)

    ★ 71.6KLast active Oct 23, 2026

  2. 2
    Open Interpreter

    Open Interpreter

    Terminal coding agent, forked from OpenAI's Codex, tuned for low-cost open models and compatible with ACP editors

    • 68.7K GitHub stars
    • Active in the last 30 days
    • Open source (Apache-2.0)

    ★ 68.7KLast active Oct 11, 2026

  3. 3
    Claude Code

    Anthropic

    Anthropic's coding agent that reads your codebase, edits files and runs commands from the terminal, IDE, desktop app, web and Slack

    • Most GitHub stars here (153,249)
    • Most weekly downloads here (7.2M)
    • Active in the last 30 days

    ★ 153.2K↓ 7.2M/wkLast active Oct 24, 2026

  4. 4
    DeepSeek-Reasonix

    esengine

    Open-source coding agent for terminal, desktop, browser and editor that edits files and runs commands and tests

    • 36K GitHub stars
    • Active in the last 30 days
    • Open source (MIT)

    ★ 36KLast active Oct 24, 2026

  5. 5
    command-code

    CommandCodeAI

    Terminal coding agent that learns from accept, reject and edit decisions through its taste model.

    • 4.2K GitHub stars
    • Active in the last 30 days

    ★ 4.2KLast active Oct 23, 2026

Search AI agents for testing → All agents

No-code builders 1 tagged

  1. 1
    Rasa Studio

    Rasa

    No-code visual tool for creating, testing and refining Rasa conversational assistants, with export to code

Search no-code builders for testing → All no-code builders

Example stacks

Combinations the catalog links as working together. These are examples built from public relations between listings, not recommendations by any vendor.

For business buyers: agents with stated pricing

Only agents whose listing states pricing are shown, with what the listing says. Check the publisher's pricing page before you buy.

AgentPricing in its listingSource
StrixStrixFreemium with a free tier; $29 per month; pricing page checked Oct 2026Pricing page
Claude CodeAnthropicPaid; $0 to $100 per month; pricing page checked Oct 2026Pricing page
Auggie CLIAugment ComputingUsage-based; $20 to $100 per month; pricing page checked Oct 2026Pricing page
Amazon Q DeveloperAmazon Web ServicesFreemium with a free tier; $0 to $19 per month; pricing page checked Oct 2026Pricing page
Augment CodeAugment ComputingUsage-based; $20 to $100 per month; pricing page checked Oct 2026Pricing page

Questions

What are the top tools for testing?
By listing rank, the top MCP server is Oh My Posh Validator, the top agent skill is cloud and the top plugin is BAML v0. Rank weighs adoption, freshness, documentation and publisher identity; money never changes it.
How many tools does the catalog list for testing?
476 listings are tagged for it: 101 MCP servers, 245 agent skills, 96 plugins, 1 agent framework, 32 AI agents and 1 no-code agent builder. Tags come from an automated enrichment pass over the top-ranked listings, so tools outside that pass are not counted.
Which AI apps do the MCP servers work with?
Of the 101 MCP servers, 95 list Claude Code, 95 list Cursor and 95 list VS Code as a supported host. Open a listing for its install command and the other hosts it names.
Do the AI agents for testing cost money?
Pricing is stated for 13 of the 32 agents: Strix (freemium with a free tier), Claude Code (paid), Auggie CLI (usage-based). The other agents state no pricing in their listings.

476 listings are tagged for this use case; the lists above show the top entries.

Related