Cursor インストールガイド
開発者向け MCP サーバーとよく使われる AI コードエディタ。
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

see README.en.md for the full English version.

Reusable XCrawl skill definitions for multi-agent runtimes, focused on API-first web data workflows. Canonical repository: https://github.com/xcrawl-api/xcrawl-skills

I'm building aven, a local-first task manager for power users and agents.

AsyncReview uses Recursive Language Models (RLM) to go beyond simple diff analysis. It autonomously explores your repository, fetches relevant context, and verifies its findings in a secure sandbox...

一个**的 AI 伙伴——不只是被动回答问题,还能根据你订阅的信息源主动判断"现在该不该发消息、发什么",在空闲时自主执行后台任务。

把课程材料变成可持续学习、可反馈、可复习、可沉淀的 Obsidian 学习系统。

大多数 AI 翻译生硬、欧化、一眼就能看出是机翻。**专为书籍级长文本设计,核心承诺是**。

An agent-led job application workflow and local progress-tracking dashboard. It works with any AI coding agent that can read a file and follow written instructions (Claude Code, Codex CLI, Cursor,...

Built with Production-Grade Plugin for Claude Code

A stateless CLI for web search, code search, library docs, and scraping — one binary, no daemon, no API server to run.

A text search engine that supports mixed Chinese and English fuzzy search

Point an agent at one base URL with one token and it can do the job: — SEO and backlinks, social and trends, people and company enrichment, ads, scraping — , with no provider signup.