Exposes self-owned AI agent plugins as tools to Claude Code via a stdio MCP server, allowing Claude to call system info, calculator, or scribe transcriber directly.
Eyes for AI coding agents: deterministic MCP server that tells the LLM which CSS rule wins, in which file, on which line — and why. Cascade verdicts, blast radius, interaction timelines, pixel-perfect audits.
attendance-engine-mcp is a Model Context Protocol server that gives AI agents
deterministic, fixture-backed tools for workforce attendance and wage-and-hour
compliance. Built on @attendance-engine/core — a pure-function, zero-deps,
100%-covered TypeScript engine — it lets Claude, Cursor, Windsurf, or any MCP
host correctly answer the questions HR/payroll teams actually ask: did this
person clock i
MCP server giving AI agents 86 tools for browser automation via Chrome DevTools Protocol, including navigation, click/fill ladders, network inspection, per-site cracks, and optional marketplace for site-specific knowledge packs.
A task-aware context compression layer for Agent workflows, RAG pipelines, and AI Coding assistants, reducing noisy logs, retrieval chunks, and code context into high-signal LLM inputs via CLI, Python SDK, and MCP.
An MCP server that brings difficulty-adaptive, multi-path reasoning to Claude Code. It implements the Actor-Critic-Planner-Reflexion (ACPR) pipeline for deep research synthesis.
A Stockfish-powered chess engine exposed as an MCP server using FastMCP. Calculates best moves, validates moves, and provides game status via MCP tools over SSE or stdio.
Local MCP server for A-share stock trading via Tonghuashun, offering account/position queries, buy/sell/cancel orders with risk controls and forced user confirmation; currently simulated with a reserved interface for real broker channels.
Provides a 3D full-body anatomy and biomechanics engine with 22 MCP tools for querying anatomical structures, connections, and clinical information, plus an interactive 3D viewer.
Enables AI agents to query Windows process, window, and console information via structured JSON instead of screenshots, reducing token usage by 94-98%.