14,315 tagged mcp, measured the same way as everything else here.
Browse within: LLM 345agents 269mcp-server 220claude-code-plugin 192antigravity 191agentic-skills 190agent 188ai-workflows 186sdk 168azure 167foundry 167claude-plugin 144agent-marketplace 142skills 116
mohamedkuch/utilia-solana-agent
Skill Codex
Use Utilia's wallet-funded x402 client for live Solana mainnet priority fees, failed-transaction diagnosis, token-risk inspection, and unsigned transaction simulation. Trigger when an agent needs machine-readable Solana preflight or post-transaction evidence and can pay $0.002-$0.008 USDC per call without an API key.
Abracadabrastartup/deusproof-mcp
Skill Claude CodeCodex
Notarize work so you can prove it existed first — a timestamped, Bitcoin-anchored public record. Use when you finish something worth protecting (code, a post, a design, an essay, a commit), when you must prove priority or defend authorship against a copy, when you need proof of prior art, or when the work is private…
Skill Claude CodeCodex
Scan a public GitHub MCP-server repository for security issues before installing or connecting to it. Calls the hosted compuute-scan API at scan.compuute.se and returns severity counts, a 0-100 score, the most severe findings, and an honest triage disclaimer. Use BEFORE recommending or installing an unfamiliar MCP…
Havix0101/arkon-vault-connector
Skill Claude CodeCodex
Use Arkon Vault before substantial work and at handoff boundaries to preserve project continuity across AI tools.
Skill Claude CodeCodex
Check whether an AI-work marketplace is worth an agent's time, wallet exposure, installation risk, or paid-work effort using a deterministic cited evidence snapshot. Use before registering with a marketplace, installing its package or skill, connecting a wallet, signing, spending, submitting work, or trusting…
Skill Claude CodeCodex
Use this skill when the user is building, securing, or auditing a browser-based AI agent (Playwright, Puppeteer, Stagehand, browser-use, or custom browser automation). Triggers on requests to "secure my browser agent", "detect prompt injection in web pages", "block my agent from visiting bad URLs", "scan this page for…
Skill Claude CodeCodex
Discover and use the Real Estate Capitale MCP server for property search, valuation, and market data in Rabat, Salé, and Témara.
bargo-ai/bargo-free-api-packages
Skill Codex
Query and analyze normalized U.S. House and Senate STOCK Act transaction disclosures with the Bargo Congress Trades API. Use when an agent needs to research recent congressional trades by ticker, member, chamber, transaction type, or date; inspect dataset freshness or aggregate statistics; build an integration with…
Skill Claude CodeCodex
Deterministic D&D Beyond character-sheet derivation with per-stat provenance. Use it whenever you need a character's real numbers: "what's my AC again?", "is this build legal?", "did anything change since last session?", "give me the party's sheets for tonight", session-start prep, or auditing a sheet a player (or a…
coastmancoastman/diem-agent-workers
Skill Codex
Convert bounded, user-supplied text into caller-defined, schema-valid JSON through the DIEM Agent Workers x402 endpoint. Use for entity extraction, record normalization, classification, or text-to-JSON jobs when the caller needs deterministic keys and machine validation and has an x402-capable HTTP client.
Skill Claude CodeCodex
MCP server exposing cryptography library functionality including encryption, hashing, and key derivation.
Skill Claude CodeCodex
MCP server for Exa web search (no API key required).
Skill Claude CodeCodex
Use this skill whenever the user wants to store, retrieve, search, or manage persistent semantic memory. This includes requests related to memory management, knowledge retention, context caching, storing information across sessions, semantic search over past conversations, tagging and organizing stored information…
Skill Claude CodeCodex
MCP server for remote debugging with gdbserver.
Skill Claude CodeCodex
MCP server exposing hashlib functionality.
Skill Claude CodeCodex
MCP server exposing Home Assistant REST API functionality.
Skill Claude CodeCodex
Local-first air quality MCP for agents. Prefer MCP tools if connected; otherwise the package CLI. Use when the user wants Wellness Air data or actions through an agent.
Skill Claude CodeCodex
Agent SEO Engine. Prefer MCP tools if connected; otherwise the package CLI.
Skill Claude CodeCodex
Delx MCP Server. Prefer MCP tools if connected; otherwise the package CLI.
kroq86/data-engineering-runtime-lab
Skill Codex
Use when the user wants to operate, diagnose, or validate the Mini Data Engine MCP runtime from Codex; prefer the MCP surface over raw shell commands, start with projecttoolcatalog and projectgetdefaults, then use healthcheck, projectrunregression, explainrun, projectcomparebaseline, and related runtime tools.
chainguard-dev/chainguard-cursor-plugin
Skill Claude CodeCodex
Migrate an existing Dockerfile to use a Chainguard base image. Use when the user wants to harden a Dockerfile, replace a Docker Hub base image, or apply a multi-stage build pattern with cgr.dev images.
OneSignal/onesignal-cursor-plugin
Skill Claude CodeCodex
Use this skill when the user wants to install, configure, authenticate, test, or troubleshoot the OneSignal Cursor plugin or OneSignal MCP server. Triggers on "set up OneSignal in Cursor", "configure the OneSignal MCP", "how do I connect Cursor to OneSignal", or any first-run plugin setup question.
frankxai/awesome-gamification-agent-skills
Skill Claude CodeCodex
Create Markdown-first skill trees, progression tracks, node cards, trials, rewards, prerequisites, YAML frontmatter schemas, and git-friendly mastery systems. Use when the user wants MD-based gamification, skill progression, learning paths, or portable skill-tree repos.
6missedcalls/openclaw-webmcp-skill
Skill Claude CodeCodex
Lets OpenClaw agents discover and invoke WebMCP tools exposed by websites via Chrome's navigator.modelContext API. Instead of clicking buttons and scraping DOM, the agent calls structured tools directly.
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: