Claude Desktop 설치 가이드

로컬 MCP 설정을 지원하는 데스크톱 클라이언트.

10501개 결과

MCP Servers

5367 개 결과
CM
clerk/mcp-tools
Developer tools

A library built on top of the MCP TypeScript SDK that makes it easier to implement MCP with auth into your MCP client and/or server.

47 035
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
BI
bitrise-io/bitrise-mcp
Developer tools

MCP Server for the Bitrise API, enabling app management, build operations, artifact management, and more.

41 035
ML
moneo/laravel-rag
Developer tools

A complete, driver-based RAG (Retrieval-Augmented Generation) pipeline for Laravel. Built on Prism PHP for provider-agnostic LLM and embedding support.

40 035
MM
mcpfind/mcp-find
Developer tools

The MCP ecosystem has grown to 10,000+ servers, but discovering and installing them remains painful. Existing directories — Glama, PulseMCP, mcp.so — are all closed source.

4 035
UU
upvoteclub/upvote-club-mcp-remote
Developer tools

Streamable HTTP MCP server for Claude.ai custom connectors.

42 035
DG
data-goblin/learn-mcp-servers
Analytics & monitoring

The purpose of the repo is to teach you how to make MCP servers. The target audience are non-technical with no real coding experience.

52 035
SM
sammcj/mcp-llm
Developer tools

An MCP server that provides access to LLMs using the LlamaIndexTS library.

79 035
FC
florianbruniaux/ccboard
Analytics & monitoring

combining Claude Code monitoring, Claude Code config management, hooks, agents, and MCP servers in a single 5.8MB binary. 89x faster startup with SQLite cache, 492 tests, 0 clippy warnings.

90 035
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
SK
sfz009900/kalilinuxmcp
Developer tools

kali linux mcp,pentest,penetration test

55 035
NN
nitrocloudofficial/nitrostack
Developer tools

The enterprise-grade TypeScript framework for building production-ready MCP servers. Decorators. Dependency Injection. Widgets. One framework to ship AI-native backends.

2천 035

Agent Skills

5134 개 결과
ZA
znyupup/ai-video-editing-skill
Developer tools

把一堆手机拍的旅行素材,用 AI Agent 自动剪成一个完整 Vlog。 你只需要提供素材文件夹,剩下的交给 Agent。

10670
SB
softnanolab/bagel
Developer tools

BAGEL is a model-agnostic, modular, fully customizable Python framework for programmable protein design.

14370
NS
nutllwhy/seedance-tvc-director
Research

一个面向 Seedance 2.5 商业广告创作的导演型 Skill。它把产品 brief、参考图和传播目标转换为 15 秒、30 秒或自定义时长的 TVC 策略、导演执行单、分镜预览与可复制视频提示词,也能根据生成成片的时间码证据给出局部重试方案。

18970
PP
poll-poll134/android-blackbox-analysis-skill
Developer tools

一个用于 的 Codex Skill。它通过 ADB 截图、UI 层级、系统运行时信息和结构化索引,把“人工逛 App”变成一套可追溯、可核验、可用于横向对比的证据材料。

10570
HE
horacelubfa/en-zh-translation-polish
Developer tools

本 skill 把叶子南《高级英汉翻译理论与实践》(第4版)的英译汉方法论,工程化为一条英译中流水线。核心信条如下:

10270
LP
littlez05/paperlocus
Developer tools

Locate every paper in the literature, not just in a summary.

12570
NN
nvidia-nemo/anonymizer
Developer tools

- using GLiNER-PII and LLM-based augmentation and validation - — LLM-generated substitute, redact, annotate, or hash (deterministic, local) - before full runs with display_record() visualization

11370
DO
dvf/opinionated-django
Developer tools

A collection of Agent Skills that give a coding agent architectural skills to build scalable, maintainable Django projects with clean separation of concerns, testability, and a full suite of best...

10970
TN
thu-nmrc/openharness
Developer tools

OpenHarness — 24/7 Autonomous AI Framework For OpenClaw

11570
WD
warpdotdev-demos/cloud-factory-demo
Code review

This repository is the canonical source for a simple cloud factory: a set of agent skills and GitHub Actions workflows for moving work from an incoming issue to a verified change.

11970
RS
rhyssullivan/skills
Developer tools

- — wrap third-party SDK clients (Stripe, Resend, AWS, etc.) with Effect using the "use" pattern: type-safe tagged errors, automatic tracing spans, config-based secrets, and clean dependency...

10470
VG
vect-g/lecture-to-hw
Data science & ML

你可能需要花时间整理材料,把问题发给大模型,review大模型给的答案,再去尝试理解某些晦涩的概念,并判断大模型的回答是否足够可信。忙完以上的一切,还要忙着去除人机味

12970