Claude Desktop 安装指南

支持本地 MCP 配置的桌面客户端。

10501个结果

MCP Servers

5367 个结果
GA
gossipcat-ai/gossipcat-ai
开发工具

Multi-agent code review mesh — orchestrates AI agents from multiple providers to review code in parallel, cross-review each other's findings, and build accuracy profiles over time.

41 055
SA
shehryarsaroya/agenttransfer
开发工具

Open-source infrastructure for AI agents — each gets an email address, folder, inbox, and API key. Move files through named inboxes instead of shared cloud credentials; signed receipts and MCP built...

48 055
ZY
zongmin-yu/semantic-scholar-fastmcp-mcp-server
开发工具

A FastMCP server implementation for the Semantic Scholar API, providing comprehensive access to academic paper data, author information, and citation networks.

161 055
FO
fxa3bah/onebrain
开发工具

Unify every AI agent on ONE local shared memory over MCP. Obsidian vault + gbrain (by Garry Tan) + Ollama. 100% offline, $0 API. Orchestrate with OpenClaw or Hermes.

48 055
AA
aarora79/aws-cost-explorer-mcp-server
开发工具

An MCP server for getting AWS spend data via Cost Explorer and Amazon Bedrock usage data via Model invocation logs in Amazon Cloud Watch through Anthropic's MCP (Model Control Protocol).

127 055
GP
googlarz/proton-mail-bridge-client
开发工具

🌉 Local-first Proton Mail MCP and CLI through Proton Bridge. Search, read, draft, send, sync, and act on mail from Claude Desktop or Terminal.

41 055
DM
dizlexic/moo-tasks
开发工具

A simple multiuser multiboard task MCP server managed via kanban board interface. Created to allow simple self hosted agent task management.

45 055
IM
instana/mcp-instana
部署与 DevOps

- - Comprehensive tool documentation with real-world examples - - Data handling and privacy information - - Comprehensive Docker deployment, multi-architecture builds, and production setup

24 055
LL
luxalgo/luxalgo-mcp-server
开发工具

The LuxAlgo ecosystem as MCP tools: free and keyless.

40 055
OO
opena2a-org/hackmyagent
开发工具

Metasploit for AI agents: scan, attack, and fix AI agents and MCP servers. Open source security toolkit.

42 055
OM
oopsyz/mcp
开发工具

This repo exposes the TMF620 command layer through two interfaces:

3 055
TA
thebnbrkr/agora-code
开发工具

Persistent memory and codebase intelligence for AI coding agents, indexes symbols, tracks sessions, and exposes structured project knowledge through an MCP server so agents stop re-reading files and...

46 055

Agent Skills

5134 个结果
AR
ayueh0102/ronnier-skill
开发工具

你以為的「中灰」,其實只反射了 的光。 CIELAB 裡 a* 乘 500、b* 乘 200 —— 那個 的比例是 **定下來的,八十年沒人動過。 1976 年 CIE 一口氣推出**色空間,不是因為需要兩個,是因為兩派人馬誰也說服不了誰。 色彩科學裡這種事很多。

8355
SM
sboghossian/master-claude-for-legal
开发工具

Master skill pack for legal teams using Claude. References, starter skills, templates, and the source webinar dataset.

6655
BS
bofai/skills
开发工具

A curated collection of practical, DeFi-focused utility skills developed by the . These skills enable AI agents to perform complex on-chain operations, payments, and identity management across...

10055
DC
dobralabs/ccos-ratos
开发工具

Kit de boas-vindas do curso Claude Code OS — Ratos de IA. Rode /setup e configure o Claude pro seu negócio em 5 minutos.

6855
ST
shinnytech/tqsdk-python
API 开发

天勤量化开发包, 期货量化, 实时行情/历史数据/实盘交易

485155
TM
thu-maic/openmaic
开发工具

Open Multi-Agent Interactive Classroom — Get an immersive, multi-agent learning experience in just one click

2万55
WP
wubing2023/paperspine
开发工具

PaperSpine is a motivation-driven skill for learning from strong academic papers, building a paper’s central argument, and rewriting manuscripts through evidence-aware blueprints, revision matrices,...

392955
JC
javaht/claude-desktop-zh-cn
API 开发

Claude Desktop Chinese Patch (macOS & Windows)

480255
SM
stas00/ml-engineering
数据科学与机器学习

Machine Learning Engineering Open Book

1.8万55
MX
maddiedreese/xteink-tamagotchi
开发工具

Display your OpenClaw / Clawdbot / MoltBot AI assistant's activity on a portable e-ink display in real-time using a .

8555
GQ
genjiyin/quantmanus
开发工具

QuantManus 是一个基于大语言模型(LLM)的智能 Agent 框架,专注于**、**和**。

8855
AQ
andrewstellman/quality-playbook
开发工具

Most code review looks at how the code is written. The Quality Playbook looks at what the code is supposed to do, and whether it actually does it.

8255