GitHub AI Agent Skills

Query MCP is an open-source MCP server that lets your IDE safely run SQL, manage schema changes, call the Supabase Management API, and use Auth Admin SDK — all with built-in safety controls. Getting started • Feature overview • Troubleshooting • - 💻 Compatible with Cursor, Windsurf, Cline and other MCP clients supporting stdio protocol - 🔐 Control read-only and read-write modes of SQL query exec

Shodh-Memory Persistent memory for AI agents. Single binary. Local-first. Runs offline. We built this because AI agents forget everything between sessions. They make the same mistakes, ask the same questions, lose context constantly. Shodh-Memory fixes that. It's a cognitive memory system—Hebbian learning, activation decay, semantic consolidation—packed into a single ~17MB binary that runs offline

This skill should be used when the user asks to "generate documentation", "document this project", "create docs", "write documentation", "update documentation", "document all APIs", "generate onboarding docs", "create developer docs", or needs comprehensive codebase documentation. Orchestrates parallel AI agents to analyze code and produce documentation files.

A Model Context Protocol server that provides read and write access to Airtable databases. This server enables LLMs to inspect database schemas, then read and write records. Step 1: Create an Airtable personal access token by clicking here. Details: - Name: Anything you want e.g. 'Airtable MCP Server Token'. - Scopes: schema.bases:read, data.records:read, and optionally schema.bases:write, data.re

A Model Context Protocol (MCP) implementation that enables secure interaction with MySQL databases. This server component facilitates communication between AI applications (hosts/clients) and MySQL databases, making database exploration and analysis safer and more structured through a controlled interface. - List available MySQL tables as resources - Read table contents - Execute SQL queries with

An MCP server for tracking and managing cryptocurrency portfolio allocations, enabling AI agents to query and optimize portfolio strategies in real time. - Portfolio Management: Add and track cryptocurrency holdings with real-time Binance prices. - Price Retrieval: Fetch current prices for any Binance trading pair (e.g., BTC/USDT). - Value History: Generate visual charts of portfolio value over ti

MCP Official Registry A Model Context Protocol (MCP) server implementation that provides Elasticsearch and OpenSearch interaction. This server enables searching documents, analyzing indices, and managing cluster through a set of tools. - generalapirequest: Perform a general HTTP API request. Use this tool for any Elasticsearch/OpenSearch API that does not have a dedicated tool. - listindices: List

After install, run st --cleanup to scan for and remove any malicious AI integrations. Security scanner detects supply chain attacks targeting AI assistants. Why this matters: Some npm packages install MCP servers that phone home to external endpoints, fetch mutable content via IPFS/IPNS, and can inject behavioral modifications into your AI sessions. These supply chain attacks are difficult to dete

The Unitree Go2 MCP Server is a server built on the Model Context Protocol (MCP) that enables users to control the Unitree Go2 robot using natural language commands interpreted by a Large Language Model (LLM). These commands are translated into ROS2 instructions, allowing the robot to perform corresponding actions. - Unitree Go2 robot - Ubuntu 20.04 or 22.04 - ROS2 environment : Humble(recommended

Convert markdown (.md) files into professional, interactive PDF documents with automatic table of contents. mcp-name: io.github.wmarceau/md-to-pdf - Automatic Table of Contents - Generated from markdown headers - Interactive Navigation - Clickable TOC links to sections - Professional Styling - Clean, readable PDF output - Code Block Support - Syntax highlighting preserved - Table Support - Markdow

An MCP server that aggregates real-time cryptocurrency news from multiple RSS feeds, helping AI agents make informed decisions in a fast-paced market. - Feed Retrieval: Fetches latest entries from specified RSS feeds, formatting them as Markdown with plain-text summaries. - Keyword Filtering: Filters feeds by keyword in descriptions or categories. - OPML Support: Import feed list from a local OPML

An MCP server that provides tools for checking latest stable package versions from multiple package registries: - npm (Node.js/JavaScript) - PyPI (Python) - Maven Central (Java) - Go Proxy (Go) - Swift Packages (Swift) - AWS Bedrock (AI Models) - Docker Hub (Container Images) - GitHub Container Registry (Container Images) - GitHub Actions This server helps LLMs ensure they're recommending up-to-da

An MCP server that tracks real-time data for major crypto-related stocks to help AI agents analyze blockchain investment opportunities. - List Crypto Stocks: Retrieve a list of crypto-related stocks (e.g., Coinbase, MicroStrategy) in a table format. - Real-Time Prices: Fetch the latest price for a specific stock, including ticker, company name, price, and timestamp. - Historical Data: Access histo

- 🔍 Multi-Provider Search - Search across Pexels and Unsplash simultaneously - 📊 Rich Metadata - Get comprehensive image details including dimensions, photographer info, and licensing - 📄 Pagination Support - Browse through large result sets with ease - 🛡️ Graceful Error Handling - Robust error handling for API failures - ⚡ Async Performance - Lightning-fast concurrent API calls - 🎯 Provider

MEMCORD v3.0.2 (mcp server) This privacy-first, self-hosted MCP server helps you organize chat history, summarize messages, search across past chats with AI — and keeps everything secure and fully under your control. Never Lose Context Again Transform your Claude conversations into a searchable, organized knowledge base that grows with you - Core Benefits - Prerequisites - Quick Start - IDE Config

A Model Context Protocol (MCP) server that connects to Heurist Mesh APIs - your gateway to Web3 intelligence. Heurist Mesh is the skills marketplace for AI agents. General-purpose AI models lack specialized knowledge about Web3 and often fail to deliver accurate results. Heurist Mesh provides 30+ specialized AI agents that are experts in crypto analytics, ready to give your AI applications the Web

A Model Context Protocol (MCP) server for Claude/Cursor that enables searching and exploring OpenAPI specifications through oapis.org. - Demo: https://x.com/janwilmake/status/1903497808134496583 - HN Thread: https://news.ycombinator.com/item?id=43447278 - OpenAPISearch: https://github.com/janwilmake/openapisearch - OAPIS: https://github.com/janwilmake/oapis The MCP works by applying a 3 step proce

A modular and extensible Model Context Protocol (MCP) server for Jira and GitHub integration, enabling end-to-end automation of developer workflows - from issue tracking to code changes and pull request management - via AI agents inside the IDE. - Jira integration: fetch issues by filters, search via JQL, and transition issues across workflows - GitHub integration: create branches, open and merge

The Model Context Protocol (MCP) is an open standard that enables seamless integration between AI assistants and external tools and data sources. Think of it as a universal adapter that lets AI assistants like Claude, Cline, and Cursor connect to specialized analysis servers. This server enhances AI assistants with deep architectural analysis capabilities, enabling intelligent code generation, dec

next-devtools-mcp is a Model Context Protocol (MCP) server that provides Next.js development tools and utilities for coding agents like Claude and Cursor. - Node.js v20.19 or a newer latest maintenance LTS version - npm or pnpm Install the MCP server for all your coding agents: Add -y to skip the confirmation prompt and install to all detected agents already in use in the project directory. Add -g

An MCP server that gives AI agents fast access to verified EVM chain information, including RPC URLs, chain IDs, explorers, and native tokens — sourced from Chainlist.org. - Efficient Data Fetching: Caches Chainlist API data to minimize requests. - Flexible Search: Case-insensitive keyword matching using regex for getChainsByKeyword. - Structured Output: Markdown responses with tabulated rpc and e

- 🚀 99% fewer API calls for batch operations (150-300 → 1) - ⚡ 88% token reduction with compact response formats - 🎯 Batch Dedupe Mode - Check 50-100 titles in one operation - 🔄 Smart Caching - 70-85% API call reduction - 🛡️ Safety Features - Multi-season confirmation, validation - 📦 4 Powerful Tools - Consolidated from 8 for clarity - 🤖 Automated Security Scanning - Dependabot for dependenc

An MCP server that provides real-time gas price predictions across multiple blockchains, powered by Blocknative. - predictgasprice: Fetches gas price predictions for a specified chain (default: Ethereum Mainnet, chainid=1), including base fee and a table with confidence levels, price, max priority fee, and max fee. - estimategascost: Estimates transaction costs based on gas limit, confidence level

An MCP server that provides AI agents with structured, real-time data on cryptocurrency investment funds, enabling deeper due diligence and portfolio intelligence. - Tools for Data Access: - getallfunds(): Retrieve a complete list of all investors and funds. - searchfunds(tier, type, sortBy, sortDirection, limit, skip): Search and filter funds with sorting and pagination. - getfundbasic(fundid): G