# MCPMods
> Directory of 5,272 Claude Code mods, 1,262 Claude skills (agent skills) and 4,418 MCP servers. Every listing has a security check (what it can access), popularity (GitHub stars or installs) and a copy-paste install command. Refreshed every 6 hours; last build 2026-10-18.

## Directories
- [Claude Code mods](https://mcpmods.com/mods/): plugins that run inside Claude Code; each shows the events it hooks and API calls it makes
- [Agent skills](https://mcpmods.com/skills/): SKILL.md workflows, each scanned for risky instructions
- [MCP servers](https://mcpmods.com/mcp-servers/): servers that connect Claude to outside systems, with data-flow checks
- [Best-of lists](https://mcpmods.com/best/)

## Guides
- [Claude Code mods vs hooks vs skills vs MCP servers](https://mcpmods.com/guides/claude-code-mods-vs-hooks-vs-skills-vs-mcp/): Which way to extend Claude Code fits your job: mods, settings hooks, skills or MCP servers, compared side by side.
- [What are Claude Code mods?](https://mcpmods.com/guides/what-are-claude-code-mods/): Claude Code mods explained: what they can do, how to install one, and how to turn them off.
- [Are Claude Code mods safe?](https://mcpmods.com/guides/are-claude-code-mods-safe/): Mods run unsandboxed with your permissions. Here is how to check one before you install it.
- [How to install Claude skills](https://mcpmods.com/guides/how-to-install-claude-skills/): Install an agent skill with one command or by copying a folder, then use it in Claude Code.
- [How to add an MCP server to Claude Code](https://mcpmods.com/guides/how-to-add-an-mcp-server-to-claude-code/): Add a local or remote MCP server to Claude Code with claude mcp add, then check it connected.

## Popular Claude Code mods
- [ruview-live](https://mcpmods.com/mods/ruview-live/): RuView live sensing in Claude Code: /ruview opens a pane beside the transcript with three views: an overview of your CSI nodes (ESP32, Realt
- [ruflo-adr](https://mcpmods.com/mods/ruflo-adr/): ADR lifecycle management — create, index, reconcile, supersede, check compliance, and link Architecture Decision Records to code via AgentDB
- [ruflo-agent](https://mcpmods.com/mods/ruflo-agent/): Agent runtimes for ruflo — local WASM-sandboxed agents (rvagent: 10 wasm_agent_*/wasm_gallery_* MCP tools, built on @ruvector/rvagent-wasm +
- [ruflo-agentdb](https://mcpmods.com/mods/ruflo-agentdb/): Substrate plugin for Ruflo memory: AgentDB controller bridge (15 agentdb_* MCP tools), RuVector ONNX embeddings (10 embeddings_* tools incl.
- [code-modernization](https://mcpmods.com/mods/code-modernization/): Guided modernization for any legacy codebase: start with /modernize, get an assessment, an interactive map, the business rules mined from th
- [fm](https://mcpmods.com/mods/fm/): Firstmate Calm for Claude Code: the sailboat working animation and conversation-only transcript presentation, sharing the per-home config/ca
- [fast-jev-compaction](https://mcpmods.com/mods/fast-jev-compaction/): Verbatim Jev-guided compaction for Claude Code sessions.
- [terminal-browser](https://mcpmods.com/mods/terminal-browser/): A browser running directly inside claude code. Preview websites, view HTML documents, and let your agent control the built in browser.
- [token-optimizer](https://mcpmods.com/mods/token-optimizer/): The Token Optimizer status bar on its own, for its tests. It ships inside the token-optimizer plugin.
- [caliber-jev-compaction](https://mcpmods.com/mods/caliber-jev-compaction/): Verbatim Jev-guided compaction for Claude Code sessions.
- [claude-council](https://mcpmods.com/mods/claude-council/): Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, Kimi, any model OpenRouter routes to, plus codex, antigravity, grok, ki
- [storybloq](https://mcpmods.com/mods/storybloq/): Project memory for Claude Code and Codex. Storybloq stores tickets, issues, handovers, and lessons in a .story/ folder inside your repo.
- [jev-auto-compact](https://mcpmods.com/mods/jev-auto-compact/): Jev-powered verbatim compaction: once context reaches 60%, prunes stale tool calls with zero generation. Skips (never falls back to the LLM 
- [shunt](https://mcpmods.com/mods/shunt/): A Claude Mod for the shunt gateway: a band above the prompt shows how much of each window is used and the time to reset — the shared account
- [lesson-cards](https://mcpmods.com/mods/lesson-cards/): Displays lesson hint cards when tool calls match known patterns. Additive surface during pilot; the classic --strict guard keeps its 12 bloc

## Popular Claude skills
- [find-skills](https://mcpmods.com/skills/find-skills/): Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can
- [grill-me](https://mcpmods.com/skills/grill-me/): A relentless interview to sharpen a plan or design.
- [grill-with-docs](https://mcpmods.com/skills/grill-with-docs/): A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
- [improve-codebase-architecture](https://mcpmods.com/skills/improve-codebase-architecture/): Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
- [agent-browser](https://mcpmods.com/skills/agent-browser/): Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking
- [frontend-design](https://mcpmods.com/skills/frontend-design/): Frontend design and UI/UX development tools
- [media-use](https://mcpmods.com/skills/media-use/): Agent Media OS for a HyperFrames project. Resolve BGM, SFX, image, icon, brand logo, voice, color grade, or LUT into a frozen local file or 
- [hyperframes-registry](https://mcpmods.com/skills/hyperframes-registry/): Search, install, and wire registry blocks and components into HyperFrames compositions. Use BEFORE hand-building any named visual — whenever
- [hyperframes-animation](https://mcpmods.com/skills/hyperframes-animation/): All animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scene transitions, broader motion-design techni
- [web-design-guidelines](https://mcpmods.com/skills/web-design-guidelines/): Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX"
- [design-mobile-apps](https://mcpmods.com/skills/design-mobile-apps/): Design mobile app screens with Sleek, edit Sleek projects, and implement their designs in React Native or HTML.
- [microsoft-foundry](https://mcpmods.com/skills/microsoft-foundry/): Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd a
- [azure-diagnostics](https://mcpmods.com/skills/azure-diagnostics/): Debug Azure production issues on Azure using AppLens, Azure Monitor, resource health, and safe triage. WHEN: debug production issues, troubl
- [azure-compute](https://mcpmods.com/skills/azure-compute/): Azure VM/VMSS router. WHEN: create / provision / deploy / spin-up VM, recommend VM size, compare VM pricing, VMSS, scale set, autoscale, bur
- [lark-doc](https://mcpmods.com/skills/lark-doc/): 飞书云文档（Docx / Wiki）内容操作：读取、创建、编辑文档，插入或下载图片附件，以及操作思维笔记。用户提供文档 URL/token（包括 doubao.com 的 /docx/、/wiki/）时使用；按 URL 路径/token 而非域名路由；`/page/` 是妙搭应用

## Popular MCP servers
- [Superpowers](https://mcpmods.com/mcp-servers/superpowers/): Structured dev workflow for AI coding agents, from design refinement to TDD implementation
- [markitdown](https://mcpmods.com/mcp-servers/markitdown/): Convert many file formats, local or remote, to Markdown for LLMs using MarkItDown.
- [servers](https://mcpmods.com/mcp-servers/servers-by-modelcontextprotocol/): Knowledge graph-based persistent memory for maintaining context.
- [storybook](https://mcpmods.com/mcp-servers/storybook/): Helps agents write and test Storybook stories for UI components.
- [netdata](https://mcpmods.com/mcp-servers/netdata/): Discovery, exploration, reporting and root cause analysis over Netdata metrics, logs, systems, containers, processes and network connections
- [Ruflo](https://mcpmods.com/mcp-servers/ruflo/): Coordinates multi-agent swarms and autonomous workflows for Claude
- [OpenSpec](https://mcpmods.com/mcp-servers/openspec/): Spec-driven development that aligns humans and AI assistants before coding starts
- [Penpot](https://mcpmods.com/mcp-servers/penpot/): Open-source design and prototyping platform with real-time collaboration
- [Chrome DevTools](https://mcpmods.com/mcp-servers/chrome-devtools/): Programmatic access to Chrome DevTools for browser control, inspection, and debugging
- [hindsight](https://mcpmods.com/mcp-servers/hindsight/): Hindsight: long-term memory for AI agents modeled on human memory.
- [Codebase Memory](https://mcpmods.com/mcp-servers/codebase-memory/): Indexes a repo into a persistent local knowledge graph of functions, classes, call chains, HTTP routes and cross-service links, using tree-s
- [posthog](https://mcpmods.com/mcp-servers/posthog/): Interact with PostHog analytics, feature flags, error tracking and more.
- [UI-TARS-desktop](https://mcpmods.com/mcp-servers/ui-tars-desktop/): Browser automation using Puppeteer, supporting local and remote browser connections.
- [MindsDB](https://mcpmods.com/mcp-servers/mindsdb/): Builds AI apps that answer questions over federated data sources via a query engine
- [Playwright](https://mcpmods.com/mcp-servers/playwright/): Playwright browser automation: interact with web pages through structured accessibility snapshots.