Cursor Руководство установки

AI-редактор кода, часто используемый с developer MCP.

10039результатов

MCP Servers

5255 результатов
AO
aanerud/outlook-desktop-mcp
Developer tools

No Microsoft Graph API, no Entra app registration, no OAuth tokens — just your local Outlook and the authentication you already have.

54 035
AA
alejandro-ao/mcp-client-python
Developer tools

This repository contains a complete tutorial on how to create an MCP (Modular Computational Platform) client in Python using FastAPI.

69 035
CN
catoncat/notion-local-ops-mcp
Developer tools

Turn a Notion into a local coding agent for local files, shell, git, and delegated tasks.

102 035
UU
upvoteclub/upvote-club-mcp-remote
Developer tools

Streamable HTTP MCP server for Claude.ai custom connectors.

42 035
OO
onlycli/onlycli
Developer tools

Turn any OpenAPI spec into a native CLI binary. No MCP, no bloat, no runtime dependencies, ONLY CLI.

44 035
WL
wulawulu/learn-claude-code-rs
Developer tools

A progressive AI Agent Harness tutorial written in Rust.

127 035
CC
capetlevrai/clipboard-vision-mcp
Developer tools

Add vision to text-only models in Opencode (, ) — , no manual file saving.

44 035
CM
congwa/mobile-agent
Developer tools

移动端 AI 自动化测试平台 —— MCP 工具 + AI Agent + 可视化操控台

43 035
NI
noemica-io/open-claude-in-chrome
Browser automation

Official Claude in Chrome gives you 58 blocked domains and two browsers. Open Claude in Chrome gives you the whole web. Clean-room reimplementation of Anthropic's browser extension. No blocklist.

178 035
IG
itallstartedwithaidea/google-ads-skills
Developer tools

Google Ads Agent Skills for Claude — campaign analysis, account auditing, safe write ops, PPC math, and MCP server integration

38 035
AG
alleybo55/gocode
Developer tools

Claude Code rewritten in Go.. High-performance AI agent harness runtime in Go. MCP server, CLI tool orchestration, session management, Kiro integration. Single binary, zero dependencies.

45 035
KS
kontext-security/agent-browser
Developer tools

Agent Browser eliminates the need to configure each MCP server in every client. Connect your clients once to Agent Browser, and it will manage all your Server-Sent Events (SSE) MCP servers for you.

63 035

Agent Skills

4784 результатов
SS
specterops/skills
Developer tools

A marketplace for LLM skills

50772
CA
cai-aa/cae-agent-hub
Developer tools

CAE Agent Hub is a collection of MCP servers, reusable agent skills, solver automation scripts, and browser result viewers for mainstream engineering simulation software.

59672
HD
heliocosta-dev/revenue-centric-design
Developer tools

A distilled, English-language playbook for designing SaaS & startup products that — packaged as an Agent Skill for Claude Code, Cursor, Codex, Copilot, Gemini, and any skills.sh-compatible agent.

44972
EE
ethpandaops/ethereum-package
Developer tools

This is a Kurtosis package that will spin up a private Ethereum testnet over Docker or Kubernetes with multi-client support, Flashbot's mev-boost infrastructure for PBS-related testing/validation,...

47472
GM
goadesign/model
Developer tools

Create your software architecture models and diagrams in Go.

46772
JY
jimmysadek/youtube-fetcher-to-markdown
Developer tools

Portable AI-agent skill: capture YouTube transcripts as Obsidian-ready Markdown with metadata, linked timestamps, language selection, and subtitle exports

47072
TS
twostraws/swift-testing-agent-skill
Developer tools

Swift Testing Agent Skill for AI Coding Assistants

40872
TS
templatical/sdk
Developer tools

Drag-and-drop email editor for modern apps — source-available, MIT after two years

48772
AF
alnitak/flutter_soloud
Developer tools

Flutter low-level audio plugin using SoLoud C++ library and FFI

42072
LA
leey21/arxiv-translator
Developer tools

新论文层出不穷,英文读得再顺也不如母语省心;我们想把这些论文变成排版规范、读着顺口的中文 PDF。

46372
AF
archlizheng/frontend-slides-editable
Developer tools

一个适用于 Claude Code / Codex 的技能,用来生成惊艳、带动画、单文件的 HTML 演示文稿,并内置浏览器编辑器:可拖拽对象、调整大小、编辑文本、重排页面、本地保存,并导出干净的独立 HTML。

46172
GF
gizclaw/flowcraft
Developer tools

FlowCraft is a Go workspace for building and evaluating AI applications without tying application code to one model provider or execution model.

41672