Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
Talk to your time tracking. Pull reports, start timers, inspect desktop activity, and turn raw Toggl data into useful recaps from Claude or any MCP-compatible client.
Figma MCP build with Rust, server with full read/write access via plugin (no REST API, no rate limits, 73 tools)
MCP server that gives AI assistants searchable access to MikroTik RouterOS documentation — 363 pages extracted live from MikroTik's official Docusaurus manual (https://manual.mikrotik.
Interactive MCP App with an inline for get_task_status.
Context Harness ingests external knowledge (files, Git repos, S3, Lua scripts) into a local SQLite store with optional embeddings, and exposes it via the ctx CLI and an MCP-compatible HTTP server so...
Treegress Browser MCP is a Treegress-maintained fork of Playwright MCP. It exposes browser automation tools for MCP clients while delegating the snapshot and locator core to the Treegress Playwright...
Read Figma files over their binary Kiwi wire protocol. Extract the full scenegraph, SVG vectors, and CSS from WebSocket frames — then push mutations back to live files from a script, no UI...
An MCP server that validates, auto-fixes, and scaffolds TwinCAT 3 XML files. Connect it to any LLM client to give your AI assistant reliable, deterministic TwinCAT code quality tooling — structural...
MCP tools for Novyx governed actions, shared memory, audit, rollback, and evidence workflows.
WaveSpeed MCP server — run any model on the live catalog (image, video, audio, 3D) with schema introspection, @path file upload, and price quotes
Stdio MCP server for the Upvote.club Public API.
Local-first persistent memory and project knowledge runtime for coding agents.
Agent Skills
Deploy any Agent as an API via POST /run . The open, multi-model runtime for AI agents — works with any LLM, on any infrastructure.
Together they produce a structured Markdown test plan and a findings report with 10-state verdicts and an explicit SUT / harness / checker / environment blame classification.
A multi-agent marathon simulation built with Google ADK and Gemini. AI agents plan a marathon route through Las Vegas, simulate the environment around it (weather, traffic, crowds), and run the race...
An agent skill for managing isolated execution environments
mim·e·o — to reproduce, to copy, to imitate.
ProductSpec is the open standard for product intent. It acts as a Product Harness for AI-native software work: what to build, what not to build, how to prove completion, and when intent changes.
Main Agent spawns Subagents like a hen with her chicks 🐔🪺🐦
交互地图 · 每日时间轴 · 出发前订票提醒 · 行前须知 · 待选航班 · 片区价位酒店
Part of the NVIDIA Cosmos project family — the training and serving framework repository.
Science Superpowers is a complete computational-science methodology for your research agents, built on a set of composable skills plus initial instructions that make sure your agent actually uses...
Guides and production-ready commands for Claude Code: skills, subagents, hooks, memory, custom commands, and conversation-history tooling.
is a config-driven dev tool for Elixir projects that manages your AGENTS.md file and agent skills from dependencies. It: