"Esoteric Software" matching MCP servers:

Provides an isolated workspace for testing candidate code, runs tests, and returns deterministic pass/fail verdicts. Enables automated grading of software engineering solutions by ensuring reproducible test runs.

Enables AI agents to perform software engineering tasks inside an isolated, deterministic sandbox—exploring repositories, reproducing failures, applying patches, running tests, and verifying solutions against hidden suites through MCP tools.

Lets AI coding agents list captured webhooks, explain why a signature failed, replay events to localhost and generate handler code. Works with Stripe, GitHub, Shopify, Slack and Twilio.

An intelligent MCP toolset for software testers that monitors code changes, analyzes test impact, recommends tests, and assesses risk, supporting multiple AI coding frameworks via dual transport modes.

Enables AI assistants to interact with iOS Simulators and Android Emulators, allowing autonomous app development, UI interaction, profiling, and debugging through natural language.

Enables AI agents to enforce a software delivery standard by validating artifacts against declarative rules, providing templates, glossary terms, and pass/fail verdicts with actionable blockers.

Functional API testing over MCP. Turns user stories into multi-step YAML test flows (chained calls, saved IDs, value and schema checks), adds read-only database checks that prove each change was stored, and generates negative and boundary tests from OpenAPI, including nested fields, where every bad input must get a 4xx and never a 5xx. Guardrails refuse writes on production-like environments, keep

Enables detection of breaking API changes across OpenAPI, Swagger, GraphQL, gRPC, AsyncAPI, and SOAP contracts, identifying affected consumers, checking deployed drift and live conformance, and generating contract tests.

Performs vulnerability scans using Trivy to generate Software Bill of Materials (SBOM) in CycloneDX format. It enables automated security auditing and dependency tracking through the Model Context Protocol.

Enables AI clients to analyze software test results and defect records, producing explainable GO, CONDITIONAL_GO, or NO_GO release-readiness recommendations with deterministic risk scoring, failed-test retrieval, defect hotspot ranking, and regression test planning.

Enables interaction with ZenTao project management software through its REST API. Supports bug tracking, product management, and issue resolution with secure authentication for streamlined development workflows.

MCP server for standardizing software module development with tools for planning, code quality analysis, security scanning, performance evaluation, documentation generation, accessibility checks, and progress tracking.

Enables autonomous software development by managing requirements, architecture, task dependency DAGs, isolated worker workspaces, execution, contract and integration verification, and checkpoints. It provides observable evidence gates so AI workers can build and verify software against reproducible contracts.

Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and visual hallucination loops.

Enables agents and tests to drive a real iOS 16.5 Safari instance running in QEMU, taking screenshots, performing touches and swipes, reading the DOM, executing JavaScript, and inspecting console and network activity. It also manages the emulated software keyboard and VM lifecycle so web pages can be exercised much as a user would on an iPhone.

Ship, conditions, needs a person, or block: one release decision from QA evidence and policy.

A universal AI-powered testing server built on the Model Context Protocol (MCP). Allows AI agents to inspect, execute, test, monitor, debug, and report on software projects.

Enables coding agents to load NASA-derived software-engineering rules before implementation, dynamically expand them as scope changes, and enforce an evidence-based final review gate.

Enables agents to select bounded software features from REA investigation evidence, extract or reconstruct them, compare behavior against scoped references, and save reusable local function folders. It keeps unknown dependencies and verification records explicit.

Enables agents to turn authorized software artifacts into verified working reimplementations through behavioral capture, clean-room synthesis, differential parity verification, and evidence-pack export. It supports CLI binaries and HTTP APIs, with policy controls and vector fuzzing.

Enables AI coding agents to receive continuous, structured software-quality feedback from Jev across multiple quality dimensions while working locally.

Enables AI agents and software engineers to investigate and resolve realistic distributed-system incidents using safe MCP-based diagnostic tools for code, logs, metrics, traces, database, and deployments.

Enables AI assistants to open real pages and return Selenium locators verified to match exactly one element, convert user stories into pytest, JUnit 5 or TestNG skeletons, run suites and report the failing locator and its line, and self-heal broken locators in CI with confidence scores, automatic re-runs, reverts and a reviewable audit trail. Works for both Python and Java test projects, including Page Objects and @FindBy annotations.

A Model Context Protocol (MCP) server that analyzes software UI screenshots using Google's Gemini AI vision, providing detailed descriptions of UI elements, layout, functionality, and accessibility.

Enables coding agents to capture and replay intermittent software failures, minimize reproductions, compare trials, search regressions, verify proposed fixes against a saved failing baseline, and retrieve investigation evidence without rerunning commands.

Enables coding agents to audit URLs, static build output, raw HTML, and whole sites for SEO issues, returning actionable findings with rule IDs, severities, fixes, selectors, and evidence, plus optional JavaScript rendering and Lighthouse performance checks.

Enables AI assistants to read and write OpenText ALM Octane and Core Software Delivery Platform data — work items, backlog triage, manual and Gherkin tests, suites, runs, attachments, traceability and release status — using entity names and natural-language filters instead of numeric IDs. Accepts names for phases, users, releases and list values, translates filters into Octane OQL, returns compact output, and can be run read-only to hide all write tools.

An MCP server that provides curated test cases and behavior specifications for common software features, enabling AI coding agents to define acceptance criteria before writing code.

Enables AI coding assistants to scan an iOS, Android, Flutter, React Native or Expo project for App Store and Google Play rejection risks, returning deterministic findings that cite the guideline section, link to the official Apple or Google page and explain how to fix each problem. Nothing leaves the machine and no AI is used in the checks.

Self improving QA agent for software teams

Enables AI coding agents to understand, run, test, diagnose, review, benchmark, and validate real local software projects through the Model Context Protocol. It provides workspace-confined safe execution, structured evidence instead of raw logs, and Git checkpoints with guarded rollback that never destroys user work.

Enables generation of test cases, edge cases, and test matrices for software testing, integrated with MCP protocol and EU AI Act compliance.

Gives coding agents local software intelligence: it surfaces the files, tests, and helpers relevant to a task before edits, flags missed callers and uncovered code during review, and returns a single SHIP / NOT PROVEN / NO-SHIP verdict when the agent stops. Everything runs on the local index with no network calls, so repository code stays on the machine.

Enables AI agents to analyse local source trees, generate starter projects for multiple targets without overwriting files, and verify generated manifests and entry files. It also exposes source and runtime inspection tools so agents can gather evidence about software artifacts within bounded, honest checks.

Enables an AI assistant to explore live pages for locators verified to match exactly one element, convert user stories or Gherkin into Playwright Test specs, run tests with per-test results that expose the failing locator, and suggest verified replacement locators with confidence scores and reasons when a UI change breaks a test. Healing is advisory only — it never silently edits tests.

Enables AI coding agents to scaffold, verify, audit, and safely modify software projects across 11 technology stacks, with rollback checkpoints, session continuity, and an evidence-based learning loop.

Enables reproducible evaluation of AI coding agents by exposing repository inspection, code editing, test running, and deterministic verification through MCP tools.

Enables deterministic, sandboxed evaluation and RL training of software engineering agents via MCP, providing repository and terminal tools, failure classification, and live dashboards.

Enables querying a registry of software failures that report success, organized by verification instrument, to discover blind spots before reporting work complete.

Bridges Notion custom agents with Claude Code to automate bug reproduction and fix implementation. It utilizes Playwright for browser automation to verify issues and Claude Code to develop and test software fixes.