Testing & QA

MCP Verification Gate: check an MCP server or an A2A agent before you connect or delegate

ogasurfproject-jpg

Check an A2A agent before you delegate, or an MCP server's measured conduct. Free, no key.

ProofSnap Verify

proofsnap

Check by manifest SHA-256, without an account, whether the ProofSnap API issued an evidence package.

io.github.SepineTam/stata-mcp

SepineTam

Let LLM help you achieve your regression analysis with Stata

S1000D Verify (S1000D Stack)

shuji-bonji

Validate S1000D data modules: XSD, BREX chain and reference resolution as one verification status.

Token safety: honeypot and rug pull check

CyberPunk11147

Stops your agent buying a coin it cannot sell: honeypot test, rug checks and an A-F risk grade.

Faxbeep

faxbeep

Test fax numbers for AI agents. Send a test fax or scan-to-email, then read what Faxbeep received.

Meshingly

DrBurakUysal

End-to-end encrypted relay that lets AI coding sessions on different machines message each other.

Eclipse Bazaar MCP

CYAN-ECLIPSE-TECHNOLOGIES-LLC

Discover agent tools by problem: every listing carries its Test Bench verdict or says it has none.

BuildPulse

BuildPulseLLC

BuildPulse for AI agents: CI runner usage, cost and savings, plus flaky tests, failures, coverage.

Argus Console — AI Agent Test Lab

igor-vii

Adversarial testing for AI agents that move money: engine battery, Ed25519-sealed verdict reports.

Bugasura

Bugasura

Bug tracking and test management: issues, test cases, sprints, runs, requirements and KB.

IYT Test

nikolai-shilin

Sailing exam practice for IYT levels and the Racing Rules: questions, mock exams, theory. EN/RU.

Verify providers before agents trust them. Settle-proven end-to-end 2026-11-02 (SELF-PROOF).

one.faf/wjttc

Wolfe-Jam

F1-grade MCP certification. 52 tests, 9 tiers (49 scored + T9 Receipt validation). Ecosystem: #2759

io.github.CloudCorpRecords/failshare

CloudCorpRecords

Shared failure knowledge for agents: check known tool failures, report failures and outcomes.

Qase Test Management

qase-tms

Official MCP server for Qase — manage test cases, runs, suites, defects via AI tools.

Endform

endformdev

Find failing, flaky, and slow Playwright tests on Endform and keep your suite healthy as it grows.

io.github.cyanheads/gnomad-genetics-mcp-server

cyanheads

Ancestry allele frequencies, LoF constraint, variant lists, and coverage from gnomAD, with ClinVar.

io.github.phillipboesger/polarion-mcp

phillipboesger

Polarion ALM MCP server for requirements, LiveDocs, work items, traceability and test management.

io.github.dbsectrainer/mcp-eval-runner

dbsectrainer

A standardized testing harness for MCP servers and agent workflows

io.github.cyanheads/fcc-broadband-mcp-server

cyanheads

FCC broadband availability, coverage analysis, and digital divide data for US geographies.

Godotwright

laaielichter

Godot 4.7 for coding agents: offline API, checks, review, safe edits, tests, play, 3D models.

Medicare Coverage

pipeworx-io

Medicare national and local coverage policy from the official CMS Coverage API.

io.github.CloudCorpRecords/promptpack

CloudCorpRecords

Check a prompt-template pack from supplied templates: variables, versions, test renders.