tokrepo-mcp-server
Search and install 200+ curated AI assets (skills, prompts, MCP configs, scripts, workflows) from TokRepo's open registry. Works with Claude Code, Cursor, Codex, and any MCP-compatible client.
README
TokRepo MCP Server
Search, browse, and install AI assets from TokRepo — the open registry for AI skills, prompts, MCP configs, scripts, and workflows.
Quick Start
Claude Code
claude mcp add tokrepo -- npx tokrepo-mcp-server
Cursor / Windsurf
Add to your MCP config (~/.cursor/mcp.json):
{
"mcpServers": {
"tokrepo": {
"command": "npx",
"args": ["tokrepo-mcp-server"]
}
}
}
OpenAI Codex / Gemini CLI
codex --mcp-server tokrepo -- npx tokrepo-mcp-server
gemini settings mcp add tokrepo -- npx tokrepo-mcp-server
What It Does
Once connected, your AI assistant can:
- Search 200+ curated AI assets by keyword or category
- Browse trending assets, filter by type (MCP, Skill, Prompt, Agent, Script)
- Get details — full documentation, install instructions, and metadata
- Install — get raw content ready to save or execute
Available Tools
| Tool | Description |
|---|---|
tokrepo_search |
Search assets by keyword and tag |
tokrepo_detail |
Get full asset details by UUID |
tokrepo_install |
Get raw installable content |
tokrepo_trending |
Browse popular/latest assets |
Example Conversations
You: "Find me a good MCP server for databases"
AI: [calls tokrepo_search] → Shows DBHub, Supabase MCP, PostgreSQL MCP with install commands
You: "What's trending on TokRepo?"
AI: [calls tokrepo_trending] → Shows top assets by popularity
You: "Install that cursor rules asset"
AI: [calls tokrepo_install] → Returns raw content ready to save
Why TokRepo?
TokRepo is the open registry for AI assets — like npm for packages, but for AI skills, prompts, MCP configs, and workflows.
- 200+ curated assets — quality-reviewed, not a dump
- Agent-native — every asset has machine-readable install contracts
- Universal — works with Claude Code, Cursor, Codex, Gemini CLI, and any MCP client
- CLI available —
npx tokrepo search "query"/npx tokrepo install <uuid>
Requirements
- Node.js >= 18
- Internet connection (queries tokrepo.com API)
Links
- Website: tokrepo.com
- CLI: npm: tokrepo
- GitHub: henu-wang/tokrepo-mcp-server
- API: tokrepo.com/.well-known/tokrepo.json
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。