Best Dap AI Skills & MCP Servers

Bun runtime adapter for MCP servers built with ModelFetch

Supabase runtime adapter for MCP servers built with ModelFetch

Next.js runtime adapter for MCP servers built with ModelFetch

MarketIntelLabs fork of the Paperclip adapter for Hermes Agent — with adapter-owned status transitions, an in-process MCP tool server (paperclip-mcp) that replaces curl-in-prompt with structured tool calls, MIL heartbeat prompt templates, and OpenRouter m

Lightweight adapter for WebMCP — define, register, and manage AI agent tools with built-in schema validation and error handling.

MCP (Model Context Protocol) adapter extension for Pi coding agent fork form https://github.com/nicobailon/pi-mcp-adapter

Browser-adapted MCP TypeScript SDK - Dynamic tool registration for W3C Web Model Context API and AI agent integration

GoPeak — MCP server for trusted Godot 4 workflows with compact/dynamic tool profiles, setup-gated LSP/DAP/runtime integrations, and migration-safe legacy compatibility.

AI-powered Adaptive Card generator — MCP server + npm library. 9 tools: generate, validate, optimize, template, transform cards for Teams, Outlook, Copilot. Designer preview included.

Adaptive trading intelligence system with Hebbian synapses, spreading activation, Wilson Score confidence, and adaptive calibration

Tuning Engines CLI, MCP server, and Python agent runtime adapters for governed model, agent, skill, and MCP workflows. Fine-tune open-source LLMs, run inference, manage datasets/evaluations, and connect LangGraph or Temporal while Tuning Engines handles p

Adaptive error memory and code intelligence system with Hebbian synapse network, hybrid search, and REST API

OpenCode plugin that injects GitLab AI Catalog agents as native opencode agents

MCP server adapter + CLI + watcher for email-agent-mcp

Adapter workspace for making Ruflo work cleanly as a DeepSeek-TUI MCP backend.

REPL-sharing MCP server — AI and humans co-drive the same visible terminal. 19 embedded adapters: shells (bash, pwsh, zsh, cmd), language REPLs (Python, Node, Deno, Lua, Racket, CCL/ABCL/SBCL Common Lisp, F# Interactive, jshell, Groovy, SQLite3), and debu

Metacognitive AI agent oversight: adaptive CPI interrupts for alignment, reflection and safety

Core interfaces and reference storage adapters for the ggui MCP server — UiGenerator, SessionStore, BlueprintProvider, AuthAdapter, plus in-memory and SQLite implementations. The pluggable seam layer @ggui-ai/mcp-server is built on.

Cloudflare runtime adapter for MCP servers built with ModelFetch

Node.js runtime adapter for MCP servers built with ModelFetch

Netlify runtime adapter for MCP servers built with ModelFetch

Self-hosted MCP server for the ggui protocol. An HTTP/MCP binding layer over @ggui-ai/mcp-server-handlers and the reference adapters from @ggui-ai/mcp-server-core — run it via `ggui serve`.

Vercel runtime adapter for MCP servers built with ModelFetch

Adaptive memory system for AI applications. Multi-strategy retrieval, cognitive scoring, knowledge graph, and self-improving ML. Connects via MCP or REST API.