SkillAvatars
Model Context Protocol servers - tools, resources, and prompts for Claude and other AI assistants.
Start Better
MCP discovery works better when people begin from a job to be done. Route them into a scene, a curated stack, or a high-signal tag before they start scanning tool cards.
Scenes
Stacks
Popular tags
Showing 24 of 3926 MCP tools
Query OpenAI models directly from Claude using MCP protocol.
This repo covers LLM, Agents, MCP Tools, Skills concepts with sample codes: LangChain & LangGraph, AWS Strands Agents, Google Agent Development Kit, Fundamentals.
AI agent runtime for Rust — type-safe state, multi-protocol serving, plugin extensibility.
The Map Everyone's Missing: LLM Knowledge Engineering in 2026 — First unified guide connecting RAG, Context Engineering, Harness Engineering, Skill Systems, Agent Memory, MCP, and Progressive Disclosure
council of models for decision
The Unitree Go2 MCP Server is a server built on the MCP that enables users to control the Unitree Go2 robot using natural language commands interpreted by a LLM.
Continuous memory + self-improvement for AI agents. Learns how you work, recalls it automatically, no commands. Claude Code & Codex.
Claude Code integration for OpenPets: automatic desktop pet status updates with one-command setup.
Agentic AI platform with pixel agent technology — autonomous code generation, PR automation & multi-tenant SaaS
This guide demonstrates how to build an Agentic AI system using Google's Agent Development Kit (ADK) and the Model Context Protocol (MCP).
Integrate Arduino-based robotics (using the NodeMCU ESP32 or Arduino Nano 368 board) with AI using the MCP (Model Context Protocol) framework from Claude Anthropic
Claude Code / Claude Desktop skill for creating and reading XMind mind maps
Copilot-style AI coding agent for VS Code, powered by DeepSeek V4.
The next-gen AI-native tensor-network-based quantum software framework
One shared macOS desktop pet for AI agents and apps, with MCP/CLI control and Codex Pets support.
Unofficial OpenEvidence MCP server — query OpenEvidence from Claude Code, Codex, and any MCP client through your own logged-in browser tab (no API key). Fire-and-forget asks, a shared relay daemon for concurrent sessions, BibTeX + Crossref citations.
Let your AI coding agent self-host any open-source app for you. 2,200+ verified recipes — provisioning, DNS, TLS, hardening. Works with Claude Code, Codex, Cursor, Aider, OpenClaw, Hermes.
Automated London flat/room hunt powered by Claude Code + Claude in Chrome + Gmail MCP. Scrapes 4 rental platforms on a cron, deduplicates via spreadsheet, prioritises HIGH/MED/LOW, and emails ready-to-send outreach.
Analyze listening patterns, build playlists, find missing albums, discover similar artists via Last.fm, fetch synced lyrics, and explore global radio. Play it all through your speakers via mpv, with a built-in web UI that makes any device with a brower act as a remote. Gives full control of your Navidrome library using natural language.
AI Skills That Actually Do Things — reusable skills for any LLM workflow
Open Agent OS for Claude Code, Codex, and Cursor: meta-agent builder, A2A Hub routing, local ontology, memory and security gates.
Open-source firewall for AI agents. Policy engine that audits and controls what OpenClaw, Claude Code, Cursor, Codex, and any AI tool can do on your machine.
Lumen — learner-owned AI education platform. Tell the AI what you want to learn: it builds you a private course in ~a minute, tutors you with course-scoped RAG + citations, and lets you share, clone & remix via a moderated catalog. BYOK, custom no-LangChain multi-agent orchestrator, golden evals in CI, MCP server. Live demo + public /eval.
C# coding-agent harness (.NET 10, Microsoft Agent Framework) — sessions, tools, permissions, providers, MCP, plugins