Claude Desktop 安装指南

支持本地 MCP 配置的桌面客户端。

12488个结果

MCP Servers

6054 个结果
GR
gillinghammer/realtime-to-mcp
开发工具

A TypeScript library that bridges OpenAI's Realtime API with Model Context Protocol (MCP) servers, enabling voice-driven tool execution.

78 060
MA
mastra-ai/personal-assistant-example
开发工具

An example personal assistant built with Mastra and MCP (Model Context Protocol) that helps with various daily tasks and information management.

77 060
MS
mcp-security-standard/mcp-server-security-standard
安全测试

The Model Context Protocol enables AI models to interact with external systems through tools, resources, and prompts.

74 060
LB
laurynas-biveinis/org-mcp
开发工具

[https://github.com/laurynas-biveinis/org-mcp/actions/workflows/elisp-test.yml] [https://github.com/laurynas-biveinis/org-mcp/actions/workflows/super-linter.yml] [https://melpa.

66 060
SM
studentofjs/mcp-figma-to-react
开发工具

This is a Model Context Protocol (MCP) server that converts Figma designs to React components. It provides tools for fetching Figma designs and generating React components with TypeScript and...

77 060
OM
ondrsh/mcp4k
开发工具

mcp4k is a compiler-driven framework for building both clients and servers using the Model Context Protocol (MCP) in Kotlin.

70 060
SD
ssdeanx/deep-research-mcp-server
开发工具

Conduct iterative, deep research using Google Gemini 2.5 Flash with Google Search Grounding and URL context. No web-scraping dependency is required.

69 060
MO
mihirrd/ollama-mcp-client
开发工具

Ollama MCP is a tool for connecting Ollama-based language models with external tools and services using the Model Context Protocol (MCP).

71 060
MS
mcp-service/media-crawler-mcp-service
开发工具

让 AI 原生使用社媒数据的MCP服务。爬虫部分参考了MediaCrawler,将其 CLI 爬虫升级为 MCP 标准工具,让 Claude / ChatGPT 直连调用,一次配置,长期可用。

69 060
RO
robdodson/ollama-mcp-db
数据库管理

An interactive chat interface that combines Ollama's LLM capabilities with PostgreSQL database access through the Model Context Protocol (MCP).

62 060
SN
sanbuphy/nanomcp
开发工具

"The question is not what you look at, but what you see." — Henry David Thoreau

74 060
FM
facebook/mcpguard-dynamic
开发工具

Kernel-level sandboxing for LLM agent tool calls made through the Model Context Protocol (MCP).

71 060

Agent Skills

6434 个结果
CO
codescene-oss/codescene-mcp-server
开发工具

The CodeScene MCP Server exposes CodeScene’s Code Health analysis as local AI-friendly tools.

6470
PM
penposs/minimax-h3-video-prompt
数据科学与机器学习

Generate and review MiniMax H3 video prompts from user goals and multimodal references.

6470
NI
noedgeai/iphoneclaw
开发工具

iphone+AI, open source apple intelligence, let agent take over your iPhone

6670
YB
yuvrajangadsingh/brandmd
开发工具

Stop Claude Code/Cursor from guessing UI. Extract any website's design system into a spec-valid DESIGN.md that passes the official @google/design.md linter.

6370
EJ
erma0/js-reverse-skill
部署与 DevOps

通用网页端 JS 逆向工程技能:统一通过 ruyipage + RuyiTrace 采集运行时日志,基于日志证据逆向还原加密参数。融合黑盒补环境(JS 层 NativeProtect)与纯算还原双路径,支持 Node.js / Python 双语言纯协议交付。已在抖音 / 小红书 / 快手 / 同花顺 / 猿人学 / 易盾等真实案例场景中得到实践。(如果最新版效果差可以使用release2.

6170
JX
jane-xiaoer/paper-collage-ppt
数据科学与机器学习

小耳剪纸风 Xiaoer Paper Collage:剪纸拼贴网页 PPT skill,14 套艺术史配色+一键换肤+滑杆+20 布局+可编辑 PPTX,文字真 HTML 永不乱码

6470
DC
drjacky/claude-android-ninja
开发工具

This repository is an package for Android development with Kotlin and Jetpack Compose. It provides a structured set of instructions, templates, and references that help agents build...

10570
BS
boheling/skillbench
开发工具

Adversarial, deterministic benchmarking for AI agent skills — measures whether a skill makes the agent measurably better. Includes biomedical eval cases.

4470
ZA
zeabur/agent-skills
部署与 DevOps

Claude Code & Codex plugin for Zeabur CLI operations, deployment, and troubleshooting.

4070
OT
onlylt/tizhi-skill
API 开发

给体制内新人的生存手册和行动指南

4070
IA
idavidov13/agentic-playwright
开发工具

Stop teaching your AI how to write tests. Hand it the rulebook.

10870
OS
owasp/secure-agent-playbook
开发工具

An open-source security playbook for AI agents. Structured, OWASP-grounded procedures that enable agents to perform security engineering tasks — from code review to AI agent security audits.

14970