mcp skills

14,308 tagged mcp, measured the same way as everything else here.

Browse within: LLM 344agents 268mcp-server 221claude-code-plugin 199antigravity 191agentic-skills 190agent 187ai-workflows 186sdk 168azure 167foundry 167claude-plugin 150agent-marketplace 149skills 117

tracker

1225

ufna/vikunja-mcp

Skill Claude Code

Use when working with team tasks in the Vikunja tracker via the "tracker" MCP tools (nexttask/claim/advance/...) — queue discipline, stage gates, when to callhuman vs returntask.

not rated 3 changed today C 45 tokens original MIT

mediacrawler-collector

1226

xwh-01/dsh-mediacrawler

Skill Codex

Use when DeepSeek Harness needs bounded, reproducible collection of posts, creator pages, first-level comments, or nested comments from Xiaohongshu, Douyin, Kuaishou, Bilibili, Weibo, Tieba, or Zhihu through a separately installed MediaCrawler checkout. Prefer ordinary web search for quick facts or a few…

not rated 3 1mo ago A 80 tokens original MIT

use-gemini-web

1227

andrewLi1994/gemini-web-bridge

Skill Claude CodeCodex

Use the user's logged-in Gemini Web session as an untrusted auxiliary model when its public YouTube audio/visual understanding, public-URL context, or an independent second analysis materially helps Codex answer or verify a request. Use for one or multiple public videos, follow-up questions, cross-checking, or a fresh…

not rated 3 3d ago A 110 tokens original MIT

openadapt-gui-write

1229

OpenAdaptAI/openadapt-agent

Skill Claude CodeCodex

OpenAdapt compiles demonstrated GUI workflows into programs. This package invokes them over MCP.

not rated 3 changed 9d ago A 23 tokens original MIT

strava

1230

davidmosiah/strava-mcp

Skill Claude CodeCodex

Unofficial Strava activity data for AI agents. Prefer MCP tools if connected; otherwise the package CLI. Use when the user wants Strava data or actions through an agent.

not rated 3 15d ago A 39 tokens copy · 86% MIT

rn-expo

1231

iksnerd/adb-mcp

Skill Claude CodeCodex

The RN/Expo dev-build recipe for adb-mcp — adbreverse before launching (or the dev client silently runs its embedded bundle), appstate to confirm it is on Metro, on the RIGHT Metro, and not serving stale JavaScript after a git checkout, then reloadapp. Use whenever driving a React Native or Expo dev build, or when…

not rated 3 18d ago A 84 tokens original MIT

readgzh

1232

sweesama/readgzh

Skill Claude CodeCodex

ReadGZH — Let AI read full-text WeChat Official Account articles. Supports standard articles and image-post formats.

not rated 3 today A 27 tokens AGPL-3.0

travel-planning-skill

1233

618034128/Travel-Planning-Skill

Skill Claude CodeCodex

Plan complete travel itineraries with a map route and a time-blocked daily schedule. Use this skill whenever the user wants to plan a trip or asks for an itinerary, route, or day plan for visiting a place — for example "plan a day in Nanjing", "help me plan a 3-day Tokyo trip", or "I want to go to X, leaving at 9 and…

not rated 4 3mo ago A 138 tokens original MIT

web

1234

Shad0wMazt3r/The-Scaffolding

Skill Claude CodeCodex

Execute web-application assessment from setup and recon through injection, access control, auth/session issues, API, and SSRF chains.

not rated 3 23d ago A 28 tokens GPL-3.0

jellyfin-kg-ingestion

1235

Knuckles-Team/jellyfin-mcp

Skill Claude CodeCodex

Natively ingest a Jellyfin library into the epistemic-graph knowledge graph via the jellyfin-mcp MCP server — push library items as typed :MediaAsset/:Book nodes with :hasGenre/:performedBy/:authoredBy links and item overviews as searchable :Document nodes (jellyfiningestlibrary), and item posters as content-addressed…

not rated 3 +1 today A 158 tokens original MIT

domain-hunter

1237

codeatlasdev/domain-hunter

Skill Claude CodeCodex

Check domain availability, generate name candidates, compare prices across 20+ registrars, check Brazilian (.br) domains via Registro.br, get trademark search URLs (INPI/USPTO/EUIPO). Use for startup naming, SaaS branding, bulk domain scanning, agent-driven naming workflows, and Brazilian market research.

not rated 3 +1 changed 3d ago A 68 tokens original MIT

il2cpp-decompiler

1238

rkuhn153/il2cpp-decompiler

Skill Claude CodeCodex

Static analysis for Unity IL2CPP games via il2cpp-decompiler-agent MCP (listdumps, loadproject, searchsymbols, getclassinfo, decompilemethod). Use when runtime is IL2CPP, GameAssembly.dll is involved, or remakes like Who's Your Daddy Remake. Always MCP-first — do not start with Il2CppStudio CLI.

not rated 3 6d ago A 80 tokens original MIT

web-asset-generator

1239

nusabyte-my/jebat-core

Skill Claude CodeCodex

Generate web assets including favicons, app icons (PWA), and social media meta images (Open Graph) for Facebook, Twitter, WhatsApp, and LinkedIn. Use when users need icons, favicons, social sharing images, or Open Graph images from logos or text slogans. Handles image resizing, text-to-image generation, and provides…

not rated 3 +1 10d ago A 78 tokens

qwen-mm-plugins-api

1240

ShuiHan268/dsh-qwen-mm-plugins

Skill Claude CodeCodex

Cloud MCP tools for understanding media, by model family. VL model: visionchat (caption/VQA), ocr, grounding (detect/locate objects). Omni model (reads frames + audio together): timestamped captioning, ASR (plain / controllable / multi-speaker diarized), temporal grounding, event counting, music captioning. Plus…

not rated 3 27d ago A 110 tokens copy · 100% Apache-2.0

fkf-use

1241

fmind/fkf

Skill Claude CodeCodex

Use an fkf base safely: inspect health, retrieve bounded evidence, resolve URIs, traverse relations, collect sources, or serve read-only MCP. Invoke for base reads or collection.

not rated 3 +1 changed 3d ago A 41 tokens original MIT

ASK191225/bugbounty-kit

Skill Claude CodeCodex

Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines, including env var intermediary patterns, direct…

not rated 3 1mo ago A 105 tokens

auzroz/ynab-mcp

Skill Claude CodeCodex

Helps build a sustainable debt-payoff plan that fits inside a real budget instead of fighting it. Use when a user says "help me pay off my credit cards", "snowball or avalanche, which should I do", "how do I set up a debt goal", "I keep going into debt for emergencies while paying off debt", or "what order should I…

not rated 3 +1 2mo ago A 87 tokens original MIT

capability-discovery

1244

444136347/dsh-capability-discovery

Skill Claude CodeCodex needs its repo

Use when a user asks to find, compare, or evaluate an existing DeepSeek Harness plugin, Skill, MCP server, agent extension, profile, or similar ecosystem capability.

not rated 3 24d ago A 39 tokens original Apache-2.0

tonytanglab/deepseek-harness-relay-mcp

Skill Codex

Dispatch and monitor an explicitly scoped, simple or medium-complexity local subtask through models available in DeepSeek Harness, including read-only review and user-authorized workspace implementation. Use when the user says “调用 Harness”, asks Harness to analyze or review, or delegates a fix, edit, refactor, test…

not rated 2 changed 2d ago A 94 tokens original MIT

memoryguard

1246

irisxc4/memoryguard

Skill Claude Code

Local-first MCP memory backend and governance console for coding agents. Auto-organize, quarantine, supersede, and rollback shared memories across multiple agents.

not rated 3 +1 changed 8d ago A 32 tokens original MIT

chartink-query

1247

shahparthiv/chartink-mcp

Skill Claude CodeCodex

Write, validate, and run Chartink stock scanner queries (scanclause strings) for the Indian NSE/BSE market. Use whenever the user asks to build a Chartink scan, screener, or scanner query, or describes stock conditions to screen for (e.g. "find stocks where RSI crossed above 60 and price above 50 SMA", "scan for…

not rated 3 +1 2mo ago A 212 tokens original MIT

pull-request-review

1248

wellkilo/RepoPilot

Skill Claude CodeCodex

Use for a GitHub pull request review run to inspect the exact head revision, changed files, and checks, then publish one evidence-backed managed review comment without approving or modifying the pull request.

not rated 3 +1 20d ago A 42 tokens original Apache-2.0

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: