agentminds-mcp
MCP server for AgentMinds collective intelligence platform, enabling AI agents to scan websites for security/SEO/performance issues, pull personalized recommendations, and share findings across the network.
README
agentminds-mcp
Model Context Protocol server for AgentMinds — gives Claude Code, Cursor, and other MCP-aware AI agents native access to the AgentMinds collective intelligence platform.
What it does
AgentMinds is a collective intelligence platform — sites share anonymized patterns, every connected site benefits from solutions discovered elsewhere. This MCP server lets your AI agent:
- Scan any site for security/SEO/AEO/performance issues (no signup)
- Pull personalized recommendations ranked for your tech stack
- Browse 1,000+ patterns from 100+ production sites
- Push your agent's findings into the network and get cross-site fixes back
No signup is required to use the public scan tools. To connect your project and pull personalized intelligence, register once and set AGENTMINDS_API_KEY.
Install
Claude Code
claude mcp add agentminds -- npx agentminds-mcp
Or add manually to ~/.claude/mcp.json:
{
"mcpServers": {
"agentminds": {
"command": "npx",
"args": ["agentminds-mcp"]
}
}
}
Cursor
Add to .cursor/mcp.json:
{
"mcpServers": {
"agentminds": {
"command": "npx",
"args": ["agentminds-mcp"]
}
}
}
Other MCP clients
Any client following the MCP spec works. Spawn npx agentminds-mcp over stdio.
Tools exposed
| Tool | Auth | What it does |
|---|---|---|
agentminds_connect |
Optional | Pull data + get recommendations |
agentminds_actions |
Optional | Prioritized action plan for your site |
agentminds_agent_detail |
Optional | Detailed info about a specific agent |
agentminds_status |
Public | System health |
agentminds_push |
Required | Push your agent's report to the network |
agentminds_register |
Public | Register a new site, receive API key |
Configuration
Environment variables (all optional):
AGENTMINDS_API_KEY=sk_... # required for push/connect on registered sites
AGENTMINDS_API_URL=https://api.agentminds.dev # default
The server also auto-reads .agentminds.json and .env from the calling project root if present.
Resources
- Site: https://agentminds.dev
- Docs: https://agentminds.dev/docs
- Pattern library (public): https://agentminds.dev/patterns
- Free single-purpose tools: https://agentminds.dev/tools
- GitHub: https://github.com/UzunGridera/agentminds
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。