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

MCP server enabling AI agents to interact with OpenProject API v3 for project management, including creating and managing work packages, projects, comments, time entries, boards, and user dashboards.

Enables discovery of a company's public feature board (Canny, Featurebase, Frill, UserVoice, Productboard) from its domain and retrieval of its most-voted requests with votes, status, comments, and the integrations customers ask for. Supports monitoring runs that surface only new requests, status changes, and vote jumps since a prior run using a saved state key.

Enables conversion of business briefs or authenticated saved projects into structured handoffs for the Lovable plugin, with both anonymous basic mode and authenticated full mode including knowledge base, SEO, WCAG, security, and roadmap guidance.

Enables agents to fetch app reviews from Apple's App Store and Google Play per country store, newest first, filtered by date or star rating, with each scheduled run returning only reviews not seen before. It also returns a per-app, per-country rating trend row with the current rating, rating count, change since the last run, and the star split of new reviews.

Pre-build reality check for AI coding agents. Scans GitHub, Hacker News, npm, PyPI & Product Hunt in parallel — returns a 0-100 reality signal with real competitor data.

Enables AI assistants to identify and quantify value leaks in organizations using Melt's methodology, providing structured estimates instead of generic vendor lists.

Enables read-only queries across App Store Connect and Google Play from one toolset, letting users list apps, track release states, and review merged store feedback without extra dependencies or credentials in demo mode.

Enables AI assistants such as Claude, Cursor, and Codex to pull structured, source-backed, dated competitive intelligence — positioning, pricing, ads, social, reviews, hiring, momentum, and exploitable weaknesses — for any company in the universe, alongside the user's own projects, reports, battlecards, timelines, and evidence. Read-only by default, with optional opt-in competitor creation and plan-gated tools for deeper analysis.

MCP server that lets LLMs read and manage BugSmash reviewer feedback while keeping the API key private.

This server assists with A/B testing by calculating required sample sizes and necessary test durations. It provides a suite of significance tests, including z-test, chi-square, and Fisher exact methods, while evaluating the risks of premature peeking.

Lets AI assistants query a live feedback collection database in plain language, retrieving entry counts broken down by type and classification status, and listing individual submissions filtered by type, urgency, or sentiment. Access is read-only and privacy-preserving, so answers can be produced without exposing submitter email addresses.

Generate production-ready Product Requirement Documents with full AINative platform awareness and persistent memory. Enables AI agents to create, validate, and manage PRDs using ZeroDB for cross-session storage and 18 tools including generation, templates, validation, and semantic search.

App Store Connect MCP server: your AI agent checks, fixes, submits and releases your iOS app. 41 tools: metadata, screenshots, builds, TestFlight, in-app purchases, preflight, submit, release, reviews, sales. Setup finishes in chat: paste your Issuer ID. Submit, release and price changes ask first; every error says what to do next. A fastlane alternative for AI agents. 7-day trial, no card.

Enables AI assistants to search, de-duplicate and route leads in a demo CRM, with read-only mode and an audit log for accountability.

Enables interaction with PostHog analytics platform, allowing users to list projects, create annotations, and search insights through natural language in Claude Desktop.

Enables coordinating multiple AI coding sessions by tracking features, decisions, and approval gates in a per-project Postgres database, with atomic IDs and commit-stamped append-only history.

Build surveys, read responses and make reports in SurveyNinja from your AI assistant. Describe a survey in plain words, check it before launch and publish it, then read the responses, get a summary or an AI report and export the results to CSV, Excel, SPSS or PDF. Hosted server, sign in with OAuth or an API key; works on every plan, Free included.

Official MCP server for FeatureJet, enabling agents to read and act on customer feedback boards: list/search posts, file feature requests, and pull top-voted planned items.

Enables reading and editing Avo tracking plans through natural language, with skills for designing new plans and working with existing ones.

Collect and analyze user feedback from any app via a single API endpoint, with MCP tools for listing, searching, and stats.

Provides an MCP Apps interface to the Upvote Club API, enabling task management with an inline progress card UI in Claude.

Enables AI agents to read-only access business intelligence in a Revinho workspace, combining Google Analytics 4, Stripe, and optionally Google Search Console to answer questions about changes, performance, revenue, underperformance, and opportunities.

Provides free, zero-marginal-cost MCP tools for structured small business teardown, competitor analysis, review intelligence, and market opportunity scanning, returning research methodology for AI models to execute.

MCP server for managing Tokei pre-launch and waitlist campaigns, wrapping the Tokei v1 REST API. Enables querying pages, stats, leaderboards, signups, and performing write operations like cloning pages and uploading media through natural language.

A User Story Map and Kanban board that a human and an AI coding agent plan together in real time via MCP, with live bidirectional sync and governance enforcement.

Enables Wildberries sellers to monitor sales, advertising, reviews, and product funnels, and adjust bids and prices, through natural language in Claude.

A federated MCP server that combines IBM's engineering-ai-hub tools with its own authoring and orchestration tools for IBM ELM, enabling AI hosts to manage requirements, models, and compliance through a single interface.

Enables external agents to inspect and interact with a local single-project workbench via MCP, providing read-only tools for state, audit, resume, readiness, comparison, impact preview, and repair candidates, while proposals are saved for manual confirmation in the workbench.

Enables car dealerships to compute total and per-vehicle holding costs for used-car inventory from stock size, average days in stock, and a daily cost rate, including savings from cutting days on the lot. It also returns dated DAT benchmark figures and comparisons so the days-in-stock can be classified against published market values.

A demo MCP server exposing an in-memory todo list via tools (add_task, list_tasks, complete_task), a resource, and a prompt, over both stdio and HTTP transports.

Public MCP server for agent-created, human-friendly, short-lived surveys. Enables agents to ask structured questions and retrieve answers.

This MCP server assists founders in customer discovery by structuring hypotheses, finding interviewees, generating call guides, and synthesizing insights to achieve product-market fit.

Enables read-only Jira Data Center insights by default, with opt-in audited write tools, sprint and release health summaries, and structured issue search via MCP.

Transforms raw business ideas into complete product strategies by orchestrating a specialized AI team for market research, competitive analysis, persona building, and financial modeling, culminating in a pitch-ready presentation.

Manages and authoring of business rules in a scenario studio tool, enabling agents to read, update, link rules, and assign them to capabilities via MCP tools.

Enables retrieval of App Store and Google Play reviews, ratings summaries, and ASO keyword rankings for any app using its store ID or package name.

MCP server for noise-reduced X (Twitter) search planning and Feedback-to-Fix engineering handoffs. Enables AI agents to generate structured search plans, filter signals, and build handoff packages via MCP tools.

A production-ready MCP server enabling AI assistants to interact with Jira projects, issues, sprints, users, attachments, and worklogs via natural language, with support for both local stdio and remote HTTP transports, dual authentication methods, and enterprise-grade security controls.

Estimates the cost and lead time for designing and manufacturing a custom plastic enclosure for an electronic device in Russia, returning development and prototype costs plus suitable production technologies, tooling costs, per-unit pricing, and timelines based on dimensions, quantity, and design type.

Enables an AI agent to audit a website for launch readiness, find suitable startup/SaaS/AI directories using filters like DR and link type, and submit product listings to SaaSCity as drafts.