Prompeteer MCP Server
An enterprise-grade toolset for AI prompt engineering that enables users to generate optimized prompts for over 140 platforms and analyze prompt quality across 16 dimensions. It also integrates with PromptDrive to manage and browse personal libraries of saved prompts directly within AI clients.
README
Prompeteer MCP Server
Enterprise-grade MCP server for AI prompt engineering. Generate expert-level prompts for 140+ AI platforms, score prompt quality across 16 dimensions, and manage your prompts in PromptDrive.
Tools
| Tool | Description | Type |
|---|---|---|
generate_prompt |
Generate an optimized AI prompt for any of 140+ platforms | Write |
list_prompts |
Browse your PromptDrive library with search and filtering | Read |
get_prompt |
Retrieve a specific saved prompt by ID | Read |
score_prompt |
Analyze prompt quality across 16 dimensions | Read |
save_to_promptdrive |
Save a prompt to your PromptDrive library | Write |
Quick Setup
Claude Desktop
Add to your claude_desktop_config.json (Settings > Developer > Edit Config):
{
"mcpServers": {
"prompeteer": {
"url": "https://prompeteer.ai/mcp/sse",
"transport": "sse"
}
}
}
Claude.ai (Web)
- Open Claude.ai
- Go to Settings > Connectors > Manage Connectors
- Click Add custom server
- Enter URL:
https://prompeteer.ai/mcp - Complete OAuth login
ChatGPT
- Open ChatGPT Settings > Developer Mode
- Click Add App
- Enter URL:
https://prompeteer.ai/mcp - Complete OAuth login
Cursor
Add to .cursor/mcp.json:
{
"servers": {
"prompeteer": {
"type": "sse",
"url": "https://prompeteer.ai/mcp/sse"
}
}
}
VS Code / GitHub Copilot
Add to .vscode/mcp.json:
{
"servers": {
"prompeteer": {
"type": "sse",
"url": "https://prompeteer.ai/mcp/sse"
}
}
}
Windsurf
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"prompeteer": {
"serverUrl": "https://prompeteer.ai/mcp/sse",
"transport": "sse"
}
}
}
Cline / Continue / Other MCP Clients
Use these connection details in your client's MCP settings:
- Server URL (SSE):
https://prompeteer.ai/mcp/sse - Server URL (Streamable HTTP):
https://prompeteer.ai/mcp - Authentication: OAuth 2.1 (automatic redirect)
Server Details
| Property | Value |
|---|---|
| Endpoint (SSE) | https://prompeteer.ai/mcp/sse |
| Endpoint (Streamable HTTP) | https://prompeteer.ai/mcp |
| Authentication | OAuth 2.1 with PKCE |
| Authorization URL | https://prompeteer.ai/oauth/authorize |
| Token URL | https://prompeteer.ai/oauth/token |
| Discovery | https://prompeteer.ai/mcp/.well-known/oauth-authorization-server |
| Scopes | mcp:read, mcp:write, mcp:generate |
| Rate Limit | 120 requests/minute |
| Session Limit | 20 per user |
Features
- 140+ Platform Support — Optimized prompt generation for ChatGPT, Claude, Gemini, Midjourney, DALL-E, Stable Diffusion, Suno, and 130+ more
- 16-Dimension Quality Scoring — Linguistic quality, structural integrity, information density, platform optimization
- PromptDrive — Personal prompt library with search, categorization, and auto-tagging
- Multi-Modal — Text, image, video, audio, and code prompt generation
- Multi-Lingual — 45+ language support
- Interactive MCP Apps — Rich UI components rendered directly in compatible clients
- Enterprise Security — OAuth 2.1 with PKCE, rate limiting, session management, audit logging
Pricing
See prompeteer.ai/pricing for current plans and pricing.
Supported Clients
Works with any MCP-compatible client including:
- Claude Desktop / Claude.ai / Claude Code
- ChatGPT (Developer Mode + Custom GPTs)
- Cursor
- VS Code / GitHub Copilot
- Windsurf
- Cline
- Continue
- Zed
- goose (Block)
- Amazon Q CLI
- LM Studio
- LobeChat
Links
- Website: prompeteer.ai
- MCP Documentation: prompeteer.ai/mcp
- Privacy Policy: prompeteer.ai/privacy
- Terms of Service: prompeteer.ai/terms
- Support: info@prompeteer.com
License
MIT — This repository contains connection configuration and documentation only. The Prompeteer platform is proprietary.
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。
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。
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。
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。
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。
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。
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。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。