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

Enables LLMs to automatically diagnose coding errors through codebase search, test execution, and live debugger integration (DAP/V8 CDP). Provides a secure, policy-gated environment for investigating failures while preventing destructive operations.

Code-aware browser testing agent — reads your codebase, understands functionality, tests every element, reports with screenshots. Works as MCP server for Cursor/Claude Code or standalone CLI.

Controls a running Chrome/Chromium browser via the Chrome DevTools Protocol, enabling navigation, JavaScript evaluation, tab management, and raw CDP commands through MCP tools.

MCP server that exposes GDB debugging as tools. An AI assistant can set breakpoints, run programs, step through code, inspect variables and memory, and examine registers — all via structured tool calls. Reverse debugging with rr is also supported.

Enables AI assistants to write and debug integration tests by providing live access to DOM structure and executing code directly in test environments.

Provides testing and quality assurance tools for AI agents via MCP, enabling generation of test cases, mock data, API mocks, coverage analysis, and assertions.

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

Enables accessibility testing of websites and HTML content using axe-core and IBM Equal Access engines. Supports WCAG compliance checking, multi-viewport testing, and provides detailed violation reports with remediation guidance.

A lightweight, local-first MCP server for executing HTTP requests and managing API collections and environments without cloud dependencies. It enables testing APIs, handling authentication, and importing OpenAPI specifications directly within MCP-compatible workflows.

Provides intelligent error detection and debugging capabilities across multiple programming languages with real-time monitoring of build, lint, runtime, console, and test errors. Offers AI-enhanced error analysis with automated resolution suggestions and context-aware debugging.

Enables MCP-capable assistants to inspect, create, measure, and review Blender production workflows for characters, rigs, animation, game meshes, facial performance, secondary motion, and PBR materials with checkpoints and visual QA.

MCP server for amazon.in — cheapest in-stock, best-value picks, and price history links.

Provides coding agents with visibility into test health through tools for flaky test detection, test quality linting, and LLM evaluation harness, enabling them to triage failures, review test quality, and check prompt changes for regressions.

A local, read-only MCP server that deterministically validates rights-aware production metadata manifests before delivery or release.

Enables Claude Code to read and write issues on the Testing Platform via natural language, including listing projects, filtering issues, creating and updating issues, and adding comments.

Connects AI agents to live observability stacks including Sentry, GitHub, Vercel, Better Stack, and Cloudflare, enabling end-to-end incident investigation, deployment correlation, root cause analysis, and regression triage.

An MCP router that connects to multiple PagerDuty sandbox environments for testing integrations like PD+Teams, PD+Jira, and more.

Enables users to describe their LLM fine-tuning job once and get the cheapest, fastest, and most balanced GPU options across a dozen cloud providers in seconds.

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 Codex to rank available tools and skills, rerank code and documentation search results, and triage saved output artifacts using Jev-based relevance scoring while leaving final decisions to Codex.

Call OpenAI Codex from Claude Code for independent second opinions, structured code review, and delegated coding tasks through a FastMCP plugin that drives the codex CLI safely.

Enables AI agents and MCP clients to drive real Chrome, Edge, Brave, and Firefox browsers through native automation protocols. It exposes tools for navigation, page snapshots, form filling, clicks, screenshots, console/network inspection, and tab management.

Enables MCP clients to open websites, capture screenshots at multiple breakpoints, and run automated design audits for issues like overflow, small tap targets, low contrast, missing alt text, tiny text, and clipped content.

An MCP relay that adds a use_jev tool to every connected server, letting the Jev model autonomously select and execute tool calls while the calling model supplies any required text values. It enables agents to delegate multi-step tool use across all configured MCP servers through a single unified interface.

Enables AI-driven 3D modeling and scene creation in Blender, allowing LLMs to create, modify, and manipulate objects, materials, and assets through natural language.

Enables AI agents and MCP hosts to drive a persistent headless Chromium browser through Playwright, navigating pages, mapping visible fields and actions, clicking, typing, scrolling, and capturing screenshots via stdio tool calls. It also powers a local AI Test Studio dashboard that generates and runs structured end-to-end test plans with assertions, per-step timing, and screenshot evidence.

Enables Codex to manage a local Claude Code companion through MCP, implementing a dual-agent workflow where Codex handles reasoning and review while Claude Code performs engineering tasks.

A modular monolith MCP server connecting multiple providers (Redash, PostgreSQL, GitHub) with unified permission, security, and auditing, enabling secure data access and tool execution.

Enables academic research through paper search across multiple databases (IACR, CryptoBib, Crossref, Google Scholar), PDF processing, and GitHub repository browsing. Features modular architecture with FastMCP-based proxy server routing to specialized academic tools.

Enables Codex to consult Claude Code for a second opinion through a local stdio MCP server, exposing the ask_claude tool for text-only reviews and recommendations using existing Claude Code authentication. Codex can request findings and tradeoff analysis without allowing Claude to edit files or run commands.

Relays a result screenshot to Slack so you can review a coding agent's output without opening the app.

Use Codex as a subagent inside Claude Code: async dispatch into a long-lived codex app-server, results pushed back into the Claude session automatically, steer/interrupt mid-task, and Codex's built-in code review.

50 tools and 400 functions for working with Excel/.xlsx spreadsheets — read/write, recalculate formulas, diff, repair broken references, and audit. Built for AI agents.

Enables following a creator's bio link to detect their newsletter, products sold, and contact emails across supported platforms and link-in-bio pages.

Gives LLM agents spatial awareness inside Autodesk Maya, enabling scene inspection and measurement, aesthetic and engineering audits, camera planning, checkpoint/rollback safety, asset import, and viewport or render previews. Agents can also execute arbitrary Python in Maya to build and verify 3D scenes against engineering rules instead of writing blind.

Enables AI agents to inspect any public domain’s web technology stack, email deliverability and DNS health (MX, SPF, DKIM, DMARC, MTA-STS, TLS-RPT, BIMI), and HTTPS security posture with typed JSON scores and remediation-ready findings, plus history, bulk checks, monitoring alerts, and reverse technology lookups.

Odds are, most of what you want to build is already open source. Tell your AI agent what you're making, and it finds it: which repos to use as they are, which to adapt, and what's left for you to write. Every repo it names is real, licensed for your use or flagged, and checked live.

Enables building and evaluating LangGraph agents over a protocol-level MCP server to measure failure rates across four agent topologies.

Provides AI assistants with specialized tools to interact with NIST's Open Security Controls Assessment Language (OSCAL) framework. It enables agents to retrieve schemas, explore models, and generate valid OSCAL documentation for security compliance automation.

Enables AI assistants to monitor and control Bambu Lab 3D printers over a local network via MQTT, including real-time status, AMS filament info, print control, and maintenance tracking. It supports guided setup, safety confirmations, read-only mode, and a built-in printer simulator.