Claude Desktop インストールガイド

ローカル MCP 設定に対応するデスクトップクライアント。

12378件

MCP Servers

5954 件
JA
janwilmake/agent-codemode
Developer tools

Let the scripts your coding agent writes call your connected MCP servers (no extra auth)

30 055
AL
astrix-labs/papez
Developer tools

Open-source causal graph memory for AI agents. 85.55 on LoCoMo under a frozen, reproducible protocol. MCP server with ACT-R scoring, spreading activation, and active forgetting.

30 055
FK
feuerdev/keep-mcp
Developer tools

1. Add the MCP server to your MCP servers:

85 055
FM
fundamentallabs/minecraft-mcp
Developer tools

This library is the Client library for a Minecraft Game Skills and MCP Integration.

74 055
CC
chrisgleissner/c64bridge
Developer tools

MCP server to control and program the Commodore 64 Ultimate, Ultimate 64, Ultimate II, or VICE.

36 055
CC
cyanheads/clinicaltrialsgov-mcp-server
Developer tools

clinicaltrialsgov-mcp-server Search ClinicalTrials.gov trials, retrieve study details and results, and match patients to eligible trials via MCP. STDIO or Streamable HTTP.

82 055
MM
marketcaper/mcp
Developer tools

Marketcaper MCP gives AI agents fresh market data and something worth posting: cited cross-asset comparisons, asset snapshots, ready-to-publish comparison packs, and hosted stock heatmap images.

92 055
RO
royshil/obs-mcp
Developer tools

An MCP server for OBS Studio that provides tools to control OBS via the OBS WebSocket protocol.

110 055
PR
possible055/relace-mcp
Developer tools

Unofficial Relace MCP client with AI features. Personal project; not affiliated with or endorsed by Relace

33 055
AS
adancurusul/serial-mcp-server
Developer tools

serial-mcp-server provides serial port access for AI workflows in two forms:

77 055
CC
codacy/codacy-mcp-server
Developer tools

MCP Server for the Codacy API, enabling access to repositories, files, quality, coverage, security and more.

61 055
LA
lgradisar/archicad-mcp
Developer tools

Archicad MCP server implementation

31 055

Agent Skills

6424 件
AP
alexisfox7/pro-long
Developer tools

Programmatic memory for long-horizon LLM agents: the harness appends everything to one log, and the agent searches it with code. 97.4% on ARC-AGI-3 (arXiv:2607.20064)

44887
HA
hoangnguyen0403/agent-skills-standard
Developer tools

v2.5.1 — trust-gated review workflows, markdown-first security handoff, expanded framework/database guidance, and a new Python backend skill pack for SDLC delivery.

52787
LC
levnikolaevich/claude-code-skills
Developer tools

Standalone engineering skills for Claude Code and Codex: review, audit, optimization, testing, product discovery, architecture, and safe publishing.

51887
RN
realrossmanngroup/no_ai_slop_writing_rules
Developer tools

Pasting raw Gemini or ChatGPT output with zero editing, or running a project with no anti-slop rules at all, is the 2026 equivalent of handing out a business card with an @aol.com email on it.

58487
GS
gotalab/skillport
Developer tools

SkillOps = Validate, manage, and deliver skills at scale.

40487
RA
rohitg00/awesome-openclaw
Developer tools

Fastest-growing GitHub repo ever - 9K to 195K stars in 66 days (18x faster than Kubernetes)

55987
YR
yurunchen/repo-docs-skills
Developer tools

Repo-Docs: Keep up with the code your agents write. An evidence atlas for agent-built code. Vibe coding makes code move faster than memory.

46087
ZS
zexuanw958-svg/travel-plan-viz
Developer tools

交互地图 · 每日时间轴 · 出发前订票提醒 · 行前须知 · 待选航班 · 片区价位酒店

33186
AB
anomalyco/browser-control
Developer tools

Browser Control lets trusted coding agents run Playwright against your existing Chromium-family browser.

33586
TA
thibautmelen/agentic-ai-systems
Developer tools

Main Agent spawns Subagents like a hen with her chicks 🐔🪺🐦

29086
AS
aws-samples/sample-well-architected-skills-and-steering
Developer tools

Reusable skills and steering that teach AI coding agents how to apply the AWS Well-Architected Framework. One set of playbooks, .

22886
SD
shenli/distributed-system-testing
Developer tools

Together they produce a structured Markdown test plan and a findings report with 10-state verdicts and an explicit SUT / harness / checker / environment blame classification.

22786