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

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 production-grade, extensible Python template for building Model Context Protocol servers with support for Streamable HTTP and stdio transports. It provides a structured framework for implementing tools, resources, and prompts with built-in authentication, observability, and background task management.

MCP server for WeChat Mini Program debugging and automation, enabling agents to perform UI operations, screenshots, and regression testing through natural language commands.

Connects LLMs to your macOS Shortcuts library, enabling interactive workflows, discovery, and management through AppleScript and CLI integration.

A production-grade TypeScript starter for building Model Context Protocol servers, supporting stdio and Streamable HTTP transports with modular tools, resources, and prompts.

An MCP server that fetches web pages and extracts clean, AI-friendly Markdown content using Mozilla Readability. It provides secure web access for LLMs with built-in SSRF protection and automated content cleaning for improved context retrieval and summarization.

An MCP server for automating virtual or physical Android devices using the Gbox SDK. It enables users to manage app installations, capture screenshots, and perform complex UI actions through natural language instructions.

Enables coding agents to compose, tune, render, mix, and audit native VOCALOID3/4 projects from scratch, acting as a production bridge between intent and finished song.

MCP server for automating AFIP/ARCA electronic invoicing, certificate management, and Web Service authorization in Argentina.

Integrates Agent Skills into LLMs by discovering skills in a configured directory and progressively loading their instructions and resources on demand through a structured disclosure pattern.

Enables comprehensive security testing and penetration testing through natural language conversations with 92+ tools for reconnaissance, vulnerability assessment, web application testing, OSINT, and reporting. Designed for authorized bug bounty hunting and security assessments.

A minimal TypeScript starter template for building Model Context Protocol (MCP) servers with auto-loading architecture for tools, resources, and prompts. Includes code generators, dual transport support (stdio/HTTP), and production-ready structure.

Provides complete access to Model Context Protocol documentation through an MCP server, allowing LLMs to query specific sections like 'Tools', 'Resources', and 'Authorization' to retrieve comprehensive protocol specifications.

An MCP server for C++ development that currently provides a server_status diagnostic tool. It validates a workspace directory and is designed to expand into build, test, and debugging capabilities.

Habitica MCP server built with Effect v4, currently exposing a hello-world tool, resource, and prompt over stdio for early development and testing.

A production-grade MCP server providing an autonomous AI agent swarm, persistent semantic memory, browser automation, multi-model reasoning, and 78+ tools for AI-first testing and development.

A lightweight MCP server that enables AI assistants to execute local development tools and retrieve system status with low latency over stdio or HTTP.

An MCP server that provides AI clients with access to developer documentation via llms.txt files. Exposes tools, resources, and prompts.

A local-first, no-API-key MCP server that enables LLMs to search the web, fetch pages, and read documents using multiple engines and smart fallbacks.

Enables AI assistants to perform Google searches with real, resolvable sources and transparent search terms.

MCP server for overseer.nvim — gives any MCP-capable coding agent running inside Neovim (Claude Code, Codex, Gemini CLI, opencode) the same visibility and control over tasks the user has: list, run, tail, restart, stop. Agent-started dev servers land in the user's own task list instead of becoming invisible orphaned processes.

Deterministic encode, decode, hash and convert for agents, on the same pipeline engine as the String Utility Belt web app, CLI and editor extensions: a pipeline built and checked in the browser runs unchanged from its share link. Base64/hex/URL, JWT, hashes, JSON/YAML/CSV/XML, dates and regex; tools to search, describe and run utilities or whole pipelines, and to detect input formats. Runs locally

Filesystem MCP server for AI assistants. Search, read, edit, and manage local files in directories you choose.

Enables AI models to access and search offline Wikipedia and other knowledge bases stored in ZIM format files. Provides intelligent content retrieval, structured browsing, advanced search capabilities, and metadata extraction for comprehensive offline knowledge access.

Read-only MCP server for Grafana Loki: lets AI agents (Claude Code, Cursor, Copilot) discover labels, read bounded LogQL pages, count lines by label or time, and export logs — across several Loki stands

Enables multi-level reasoning with configurable depth levels, session-based state management, structured thought input, and real-time trace resources.

Relays error logs from other MCP servers when an LLM call fails and the returned error message is unclear, helping the model handle errors more intelligently.

Enables LLMs to interact with the AT Protocol ecosystem, including Bluesky, through natural language. Supports public data access without authentication and full write operations with authentication.

Live Japan seasonal travel data from Japan Meteorological Corporation. 12 tools covering cherry blossom (sakura) forecasts, autumn leaves (koyo), fruit picking, flowers, festivals, and 3-day weather. 1,700+ GPS-tagged spots updated daily at 9AM JST. Works via npx or hosted HTTP endpoint — no auth required.

Enables AI assistants to read, search, and traverse your entire reMarkable library, including handwritten notes via OCR.

A TypeScript-based server that enables programmatic management of pseudo-terminal sessions. It allows users to spawn, control, and interact with terminal processes in real-time through the Model Context Protocol.

Deterministic Swiss Ephemeris (pyswisseph < 1.5 ms, Zero-Auth, Rule 14 Zero-Knowledge Privacy) MCP Server computing natal charts, Placidus houses, Draconic nodes, 7 Eternal Wisdoms (Western Astrology, Mayan Tzolkin, Vedic Jyotish 27 Nakshatras, BaZi & Wu Xing, I-Ching 64 Hexagrams, Human Design, Tarot & Kabbalah), 3D Soul Synastry, and Family Constellations (CA/ES/EN).

Lets AI assistants discover public Socrata open-data portals, search their datasets, inspect schemas, and run bounded read-only SoQL queries to answer questions with live government data. All access is strictly read-only and results come straight from the publisher's portal.

Let AI agents search and read your mail: on-premises Microsoft Exchange (EWS, no cloud API or admin setup) and any IMAP mailbox, tested on Mail.ru and Gmail. Text inside PDF, Office and ZIP attachments is searchable in Russian and English. Runs from a local copy, and read-only is enforced at the protocol level.

Enables AI assistants to generate real images via multiple models (OpenAI, Gemini, Recraft, Seedream, Grok, Arrow) and returns usable file paths instead of base64 data.

Unofficial MCP server for the messdienst24.de utility portal, providing tools to retrieve heating and hot-water consumption data, download PDF reports, and compare usage trends.

Provides AI agents with access to the Colyseus documentation, enabling searching, reading, and listing of documentation pages.

MCP server that connects AI assistants to your reMarkable tablet, enabling reading, searching, and traversing handwritten and typed notes via OCR.

MCP server for the ReactUse library. Exposes 110+ React Hook signatures, examples, and API metadata so AI coding assistants can discover and use any hook from @reactuses/core directly.

Enables AI assistants to create, edit, and publish micropages and posts from markup, with optional controls for subscriber emails, project deletion, and form submissions.