"The most downloaded Minecraft Plugin (MCP) right now" matching MCP servers:

Provides a bounded, write-controlled interface to the Coolify v4 API with per-call credential selection and accidental-write controls.

Integrates Qlane test management into AI coding editors, enabling agents to view projects, test targets, and test case counts, and plan tests for local diffs.

Enables deploying and managing projects across AWS, Google Cloud, Azure, DigitalOcean, Hetzner, and Vercel directly from Claude Code, with tools for instance lifecycle, domains, environment variables, backend services, databases, webhooks, and GitHub integration.

A bundled MCP server that lets Claude work with any Gitea instance — gitea.com or self-hosted — covering repositories, files, branches, issues, pull requests and reviews, organisations and teams, Gitea Actions runs and logs, releases, webhooks and notifications. It exposes 126 tools with tiered read/write/destructive/admin permissions, secure token handling, and workflow skills for tasks like pull request review and CI failure analysis.

A LangGraph-powered MCP server for infrastructure orchestration with autonomous subagents.

Enables creating, inspecting, validating, publishing, and debugging VibeX DAG Workflows as source files, with run control and safe revision management.

Enables AI assistants to inspect and operate Jenkins instances: listing jobs, builds, queue items and nodes, reading incremental build logs and pipeline stage views, and triggering, stopping or cancelling builds with read-only guards.

. A good description should be concise and describe what the server enables users to do, e.g. * Enables to interact with WordPress sites...' Then a huge block? Actually the user message includes the README content inside tags, then after the readme, there is a large block of text starting with '{

Enables an AI to statically audit GitHub Actions workflow files, parsing YAML with accurate line numbers and reporting findings about on: key quirks, expression injection risks, unpinned actions, effective token permissions, and cron scheduling.

Enables Claude Code sessions to wait for a durable, exact-head GitHub pull-request review and continue the same review/fix/push loop without polling, using Supabase durable state and Realtime wake-ups via ordinary stdio MCP.

Enables uploading source data, queuing Windows DTS Engine publishing jobs, monitoring them, and downloading hash-verified 3DT results.

tailtest-cline is a Cline plugin that automatically generates and runs tests every time the agent edits a source file. https://github.com/avansaber/tailtest-cline

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.

Self-hosted coding agent that runs Claude Code or Codex in your own infrastructure and works from Slack. Exposes codebase investigation, file edits, branch and PR creation, allowlisted command execution, CI status and an audit log as MCP tools, keeping every credential behind the tool layer instead of handing it to the model.

A local MCP server for Jenkins that provides 17 tools to interact with Jenkins jobs, builds, logs, SCM, and test results via REST API, no plugin required.

Provides Xcode build, test, and package management operations through the Model Context Protocol.

Enables AI assistants to review GitLab merge requests by fetching changes, analyzing diffs, adding comments, and managing approvals through the GitLab API. Supports complete merge request analysis, file-specific reviews, and version comparisons.

The most comprehensive Azure DevOps MCP server & CLI — 13 tools, 82 actions, single Go binary.

A comprehensive MCP server with 53 tools for managing Jenkins CI/CD operations, including job, build, pipeline, node, credential, and plugin management, enabling AI assistants to control Jenkins servers through natural language.

Unified capability catalogue with formally verified cartridges, distributed community hosting, and the Teranga menu system for single gateway access to a vast rabbfe of MCP, LSP, NeSy and related servers.!

Enables AI assistants to manage Prismatic integrations, components, and flows via the Model Context Protocol, supporting code-native integration development and component lifecycle.

Enables AI assistants to interact with the Cycloid platform for infrastructure management, including blueprint discovery, stack creation, pipeline listing, and event monitoring via natural language.

Maestro is the simplest and most effective UI testing framework for Mobile and Web. Maestro MCP allows you to control emulators, interact with apps, write and automatically debug UI tests on Claude Code, Cursor or Windsurf.

Deploys the current folder or a GitHub repo to a live HTTPS URL on Dockhold, and lets AI tools read status/logs, set variables, and resize apps and managed databases.

MCP server plugin for the tsdevstack CLI, enabling AI agents to manage infrastructure, deployment, and project state with 54 tools and 12 resources.

Publish websites from Claude, the terminal, or CI — drop a folder, get a link that doesn't expire. Wraps the nippy.host publish pipeline: create sites, update in place, read files, passwords, SEO settings, and visitor analytics.

Enables uploading and managing iOS/Android apps on the PGYER platform through MCP tools.

Serves MoleSignal's tools over stdio to AI agent tools such as Claude Code, Cursor, Codex, VS Code, or Gemini CLI, enabling them to query logs, metrics, traces, incidents, approvals, deployments, and other capabilities under the user's permissions and organization policy.

Enables connecting your service to the LAF bot by providing a minimal MCP server that reports critical signals and additional risk-annotated tools, with built-in submission checks and CI.

Budget & cost control for AI agents: hard per-agent spend caps, rate limits, idempotency, and human-in-the-loop approval — enforced before each LLM call, not after the invoice. One hosted MCP endpoint (no proxy or self-hosting), settled via x402 (USDC on Base).