LLM & AI Agent Skills

Every multi-step tool workflow burns an LLM round-trip per step. The agent calls tool A, waits, sends the full context back to the model, gets a decision to call tool B, calls it, sends everything back again. Each round-trip re-transmits 2K–10K tokens on what is essentially plumbing. For a session with 20 two-step workflows, that's 20 wasted model calls, ~100K wasted tokens, and 20–40 seconds of a

An MCP server that gives AI assistants safe, read-only access to SQL Server databases. Every query is parsed into a full AST using Microsoft's official T-SQL parser — not regex — so comment injection, string literal tricks, and encoding bypasses are blocked at the syntax level. Prerequisite: .NET 10.0 runtime 2. Configure — create ~/.config/sqlaugur/appsettings.json (Linux/macOS) or %APPDATA%\sqla

An MCP server (stdio transport) that wraps Hugging Face's LocalPythonExecutor (from the smolagents framework). It is a custom Python runtime that provides basic isolation/security when running Python code generated by LLMs locally. It does not require Docker or VM. This package allows to expose the Python executor via MCP (Model Context Protocol) as a tool for LLM apps like Claude Desktop, Cursor

� Migrate to MCP Platform • 💬 Discord Community • � Legacy Docs Zero-configuration deployment of production-ready MCP servers with Docker containers, comprehensive CLI tools, and intelligent caching. Focus on AI integration, not infrastructure setup. That's it! Your MCP server is running at http://localhost:8080 Perfect for: AI developers, data scientists, DevOps teams building with MCP. Deploy M

A Model Context Protocol (MCP) server for interacting with Bugsnag. This server allows LLM tools like Cursor and Claude to investigate and resolve issues in Bugsnag. - Organization & Project Navigation: Easily browse your Bugsnag hierarchy - Error & Event Filtering: Find specific issues with powerful filtering options - Detailed Stacktrace Viewing: See formatted stacktraces with source code contex

A Model Context Protocol (MCP) server that provides access to the Tatum Blockchain Data API and RPC Gateway, enabling any LLM to read and write blockchain data across 130+ networks. Visit official MCP webpage for more details and to get your Tatum API key. - 130+ Blockchain Networks: Bitcoin, Ethereum, Solana, Polygon, Arbitrum, Base, Avalanche, and many more. - 🔗 Blockchain Data API: Blocks, tra

- About the pgEdge Postgres MCP Server - pgEdge Postgres MCP Server - Choosing the Right Solution - Best Practices - Querying the Server - Installing the MCP Server - Quick Start - Quickstart Demo with Northwind - Deploying on Docker - Deploying from Source - Testing the MCP Server Deployment - Configuring the MCP Server - Specifying Configuration Preferences - Using Environment Variables to Speci

👋 join us on Discord and WeChat If you like Dingo, please give us a ⭐ on GitHub! Dingo is A Comprehensive AI Data, Model and Application Quality Evaluation Tool, designed for ML practitioners, data engineers, and AI researchers. It helps you systematically assess and improve the quality of training data, fine-tuning datasets, and production AI systems. 🎯 Production-Grade Qua

A Model Context Protocol (MCP) server for querying NIST National Vulnerability Database (NVD) API endpoints. This MCP server exposes tools to query the NVD/CVE REST API and return formatted text results suitable for LLM consumption via the MCP protocol. It includes automatic query chunking for large date ranges and parallel processing for improved performance. Base API docs: https://nvd.nist.gov/d

Project Synopsis

mem0-mcp-server wraps the official Mem0 Memory API as a Model Context Protocol (MCP) server so any MCP-compatible client (Claude Desktop, Cursor, custom agents) can add, search, update, and delete long-term memories. The server exposes the following tools to your LLM: All responses are JSON strings returned directly from the Mem0 API. There are three ways to use the Mem0 MCP Server: 1. Python Pack

Write less code and say less about it. Honey (I Shrunk the AI) by GreenPT is a cross-tool coding skill that cuts AI coding-agent token usage and LLM API costs — making agents emit less code and less prose without losing correctness. It works with Claude (claude.ai and the API), Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI, Windsurf, Cline, OpenClaw, Kiro, and Kilo Code. Three independent

audit-prompt-caching is a portable Codex/agent skill for finding why LLM cache reuse fails across the request path: prompt/prefix caches, provider cache telemetry, cache-aware routing, agent tool stability, Bedrock checkpoints, OpenRouter routing drift, provider migration risk, and vLLM/SGLang KV reuse. LLM cache reuse usually fails silently. A timestamp in the system prompt, shuffled tool schemas

An MCP (Model Context Protocol) server that lets Claude, ChatGPT, and other LLM agents search and discover APIs using natural language via Semantic API. Ask for any API capability in plain English and get back endpoint details, parameters, auth info, and code snippets. Or run directly with uvx: Sign up at semanticapi.dev to get your API key. Add to your Claude Desktop config (~/Library/Application

Apple Health MCP Server Apple Health Data Exploration Connect your Apple Health data with any LLM that supports MCP. Talk to your data and get personalised insights. This demo shows how Claude uses the apple-health-mcp-server to answer questions about your data. Example prompts from the demo: - I would like you to help me analyze my Apple Health data. Let's start by analyzing the data types - chec

The CockroachDB MCP Server is a natural language interface designed for LLMs and agentic applications to manage, monitor, and query data in CockroachDB. It integrates seamlessly with MCP (Model Content Protocol) clients, such as Claude Desktop or Cursor, enabling AI-driven workflows to interact directly with your database. - Cluster Monitoring - Database Operations - Table Management - Query Engin

Give AI assistants the power to query your Prometheus metrics. A [Model Context Protocol][mcp] (MCP) server that provides access to your Prometheus metrics and queries through standardized MCP interfaces, allowing AI assistants to execute PromQL queries and analyze your metrics data. [mcp]: https://modelcontextprotocol.io - Prometheus server accessible from your environment - MCP-compatible client

Jotdown is a Model Context Protocol (MCP) server that allows large language models (LLMs) to interact with Notion and also generate Markdown Books. It provides two primary tools for LLMs: - 👉 Notion Integration: Create or update pages in Notion with content generated by the LLM. - 👉 Mdbook Generation: Generate a mdbook from content and manage the structure. Jotdown enables LLMs to seamlessly int

The Redis MCP Server is a natural language interface designed for agentic applications to efficiently manage and search data in Redis. It integrates seamlessly with MCP (Model Content Protocol) clients, enabling AI-driven workflows to interact with structured and unstructured data in Redis. Using this MCP Server, you can ask questions like: - "Store the entire conversation in a stream" - "Cache th

This is a Model Context Protocol (MCP) server designed specifically for AI agents and LLM applications. It acts as a bridge between artificial intelligence systems and the comprehensive OpenStreetMap tagging knowledge base provided by the official @openstreetmap/id-tagging-schema library. Current Status: Production-ready MCP server, actively maintained and continuously improved. The service is dep

A Model Context Protocol (MCP) server that interfaces with the HackMD API, allowing LLM clients to access and interact with HackMD notes, teams, user profiles, and history data. - Get user profile information - Create, read, update, and delete notes - Manage team notes and collaborate with team members - Access reading history - List and manage teams - Dual transport support: Both HTTP and STDIO t

CSL-Core (Chimera Specification Language) is a deterministic safety layer for AI agents. Write rules in .csl files, verify them mathematically with Z3, enforce them at runtime — outside the model. The LLM never sees the rules. It simply cannot violate them. Originally built for Project Chimera, now open-source for any AI system. This doesn't work. LLMs can be prompt-injected, rules are probabilist

A Model Context Protocol (MCP) server implementation that provides the LLM an interface for visualizing data using Vega-Lite syntax. The server offers two core tools: - Save a table of data agregations to the server for later visualization - name (string): Name of the data table to be saved - data (array): Array of objects representing the data table - Returns: success message - visualizedata - Vi

-brightgreen) A Model Context Protocol (MCP) server for analyzing technical debt across multiple programming languages. Designed to integrate with GitHub Copilot and other MCP-compatible tools. - Multi-language support: JavaScript, TypeScript, Python, Java, Swift, Kotlin, Objective-C, C++, C, C, Go, Rust, Ruby, PHP - Comprehensive analysis: Detects various types of tech debt including code quality