"Automating Testing and Debugging for LLMs in Production" matching MCP servers:

MCP server for testing GitHub Actions workflows locally using nektos/act.

Enables automated testing and coverage reporting for MCP services with test execution, file generation, and mock service creation. Provides comprehensive testing infrastructure including Jest integration, coverage reports, and health checks for the MCP ecosystem.

An MCP server that executes tox commands to run Python tests within a project using pytest, allowing users to run all tests or specific test groups, files, cases, or directories.

Enables submitting FMF-based test requests to Testing Farm and listing available OS composes for testing.

Enables local, read-only static inspection of Python/FastAPI, Docker, and GitHub Actions release evidence through a stdio interface, returning rule and instance findings without importing or executing target code.

Analyzes Testing Farm jobs, checks job status, and investigates failures with detailed error information.

A multi-language testing automation server that enables AI assistants to discover, plan, and execute tests across six major programming languages. It provides comprehensive tools for repository scanning, automated test execution, and detailed coverage reporting.

Automates Java Maven testing workflows with decision table-based test generation, security vulnerability scanning, JaCoCo coverage analysis, and Git automation.

Enables interaction with Azure DevOps through natural language in Cursor IDE. Supports work item management, pull requests, builds, releases, test management, and guided workflows for development teams, QA testers, and release management.

Orchestrates end-to-end testing of AI-powered incident remediation workflows through declarative YAML scenarios, fault injection, AI response evaluation, and automated command execution with comprehensive reporting.

A specialized MCP server for QA engineering. It provides tools for user story analysis, test strategy, BDD/Gherkin scenarios, contract testing, integration tests, performance plans, security checklists, and CI/CD pipeline generation, accessible from any MCP-compatible IDE or client.

Monitor failing GitHub Actions workflows, auto-fix them with OpenCode, and retry the run — driven by a workflow_run webhook, coordinated through an MCP server.

Enables state-aware Terraform/OpenTofu plan evaluation against live AWS topology and CloudWatch telemetry, detecting reliability blast radius and FinOps waste before merge.

A Model Context Protocol server implementation that allows AI models to interact with and manage Spinnaker deployments, pipelines, and applications through a standardized interface.

Checks the outcome after an agent handoff, when a request, 200 or ack only shows the handoff. Reads one field of one exact public HTTPS JSON record, with a same-site known-good control, for 20-120 s. Returns PROVED, DISPROVED or INCONCLUSIVE with a signed receipt you can verify. 5 free checks, then USD 1 per completed check, by card (Stripe Checkout) or existing Link wallet. INCONCLUSIVE is free.

Integrates Cline with Azure DevOps services, enabling access to work items, repositories, and pull requests through configurable MCP tools.

Provides AI assistants with comprehensive access to Azure DevOps services including work items, repositories, pull requests, wikis, builds, pipelines, and test plans through 25+ MCP tools with multi-project support.

Provides a standardized way for MCP clients to interact with Apache Airflow's REST API, supporting operations like DAG management and monitoring Airflow system health.

Provides ChatGPT read-only access to inspect repositories, code, merge requests, pipelines, and CI logs on self-managed GitLab instances, including those reachable only from a private network or VPN.

Enables comprehensive GitHub workflow automation including Actions monitoring, PR management, code search, file operations, and repository management through a code-first architecture that reduces token usage by 98%.

Enables AI assistants to interact with Argo CD applications, managing clusters, applications, and resources through natural language.

Provides integration with Apache Airflow's REST API, allowing AI assistants to programmatically interact with Airflow workflows, monitor DAG runs, and manage tasks.

MCP server that enables AI assistants to manage Azure DevOps resources including Work Items, Git repositories, pipelines, and user identities.

MCP server for the Argus E2E Testing Agent, enabling AI coding assistants to perform browser testing, quality intelligence, CI/CD integration, discovery, time travel debugging, visual AI testing, correlation analytics, and API testing directly from the IDE.

A remote MCP server that provides AI agents access to the Rootly API for incident management, allowing users to query and manage incidents, alerts, teams, services, and other incident management resources through natural language.

Supply-chain gate for AI agent skills and MCP servers: poison-scan tool definitions, hash-pin the vetted set into a lock file and verify drift in CI. truecopy-mcp is a drop-in stdio proxy that filters a live server's tools/list down to its pinned, unmodified, unpoisoned tools.

Security auditor for CI ecosystems that detects supply-chain and injection flaws in CI/CD configuration files across seven CI platforms, providing taint analysis, remediation, and compliance scoring.

MCP server with the watch_ci tool that polls GitHub Actions until a commit's CI run finishes, then returns the outcome and failed log tail in one call.

A lightweight, powerful, and flexible workflow engine that executes tasks defined in YAML configuration files.

Enables AI agents to audit Kubernetes manifests for configuration traps that pass linters but silently break production, via read-only tools to audit YAML, list known traps, and explain trap details.

Local CI/CD engine for AI agents. ActionD listens to LGH git events and runs plugin jobs (Go/Python/Java/web toolchains) in isolated checkouts, with structured results, root-cause failure diagnosis, approval gates, and auto-rollback. The MCP server exposes 23 tools, including dev_cycle_run (commit → CI → structured verdict in one call) and actiond_diagnose for failed-job analysis.

Enables AI clients to assess infrastructure-as-code deployment risk, generate incident response runbooks, review CI/CD delivery readiness, and calculate SLO error budgets through structured advisory tools. Runs locally over stdio without cloud credentials or external API calls, returning guidance for platform work, pull request review, and production readiness checks.

Record an agent's MCP tool-call workflow once, replay it deterministically for zero tokens, and get a receipt — a snapshot-testing and deterministic-execution layer for Agent Skills.

Provides disposable email inboxes for AI agents to automatically receive and extract OTPs and magic links, enabling seamless email verification during autonomous workflows.

An MCP server that enables AI assistants to discover and execute Nox sessions for project automation tasks like testing, linting, and building. It provides tools to list available sessions and run them using specific Python versions, tags, or keyword expressions.

Enables AI agents to interact with Appcircle mobile CI/CD platform for build management, signing identities, testing distribution, and reporting.

Deploy, run and manage apps on your own self-hosted AppCrane from any MCP client. 62 tools: create an app, push code, deploy to sandbox, check health and logs, provision a managed Postgres, MariaDB, MongoDB or Redis, and promote to production after review. Your instance, your SSO, your data. Repo: https://github.com/gitayg/appcrane-mcp · npm: appcrane-mcp · Site: https://appcrane.dev

A Model Context Protocol server that monitors shadow-cljs builds and provides real-time build status updates for ClojureScript projects, allowing LLMs to verify build status after making code changes.

Deploys and manages projects on Swigs Cloud from any MCP client, turning folders or git repositories into live HTTPS sites in about two minutes.

CI health reports for GitHub Actions: flaky tests named from logs, wasted compute priced in dollars, zombie crons, PR feedback time, plus 21 lint rules with safe auto-fixes. Read-only MCP tools wrap the same Go binary.