Cursor Руководство установки
AI-редактор кода, часто используемый с developer MCP.
MCP Servers

⚠️ This implementation stores OAuth credentials in ./mnt/mcp-creds/ which are currently committed to the repository. Proper OAuth flow for MCP servers is coming soon to the Agencii platform.

Evidence-grounded repository audit CLI - deterministic scanner, MCP server, live dashboard, and a GitHub Action that posts PR diffs.

Total recall for your terminal. Shared memory for your AI agents.

built by an autonomous agent · sibyl labs llc

An MCP server that queries public SearXNG instances, parsing HTML contents into a JSON result

Spring AI Playground is a cross-platform desktop app for building, testing, validating, and executing MCP tools in a controlled local environment.

A domain harness for AI-assisted mobile development and testing. Unified device logs, network traffic interception, and UI automation — exposed through APIs and MCP tools that let AI agents...

An MCP server that lets AI agents read and draw on the Figma canvas — safely. Paired with a Figma plugin, it provides structured verification, safe-by-default drawing, and resilient multi-window...

Your AI assistant now remembers everything. Forever. Across every conversation.

Stop rewriting your tools. Just adapt them.

Use any MCP server or HTTP API as a standard CLI command. A lightweight daemon + CLI that turns remote MCP tools and configured HTTP endpoints into native shell commands your agent or script can call...

Streamable HTTP MCP server for Claude.ai custom connectors.
Agent Skills

KSensor is a Kotlin Multiplatform library for observing device sensors and system states. Each sensor or state is grouped into its own plugin, allowing you to include only the features you need.

Riffpad bridges the AI coding CLI running on your machine to your phone, so a long refactor doesn't chain you to the desk:

An infinite-canvas image board that generates through the you already pay for — no API key, no per-image billing, and none of your Codex quota.

一套开箱即用的 Claude Code Harness Engineering 模板 新项目和已有项目均可使用

A grumpy senior code reviewer for Claude Code and Codex. He reviews your changes, tells you what's wrong, and never suggests fixes.

Your entire AEO/GEO/AI Visibility, technical SEO + web analytics stack.

/secretary を実行すると、対話的にあなたの役割・日常・ニーズをヒアリングし、Markdownベースの管理フォルダを自動生成します。

This repo supports not only KIMI LLM but also various API keys! Like OpenAI, Anthropic, etc. Default config templates are in docs/; use kimix --config=xx.json after setup.

Claude Legal Turkish, Anthropic'in açık kaynaklı yapısını temel alan Türkiye uyarlamasıdır. Amaç, aynı plugin/skill iskeletini koruyarak hukuki içerikleri Türk hukuku, Türkiye yargı sistemi ve yerel...

Agent Access allows users to provide credentials from their password manager to remote systems, without exposing their entire vault.

🤖 Autonomous development orchestrator for the BMad Method. Runs fully autonomous parallel multi-agent pipelines through the full story lifecycle (create → dev → review → PR) driven by your sprint...

- 大模型调用是怎么做的 - Agent 为什么不是普通聊天机器人 - Claude Code 风格的 coding agent 是怎么循环运行的 - 工具调用、子代理、上下文压缩、任务系统、多 Agent 协作是怎么一点点叠加出来的