holdify-mcp
Enables AI assistants to manage API keys, check usage, and debug authentication issues for the Holdify API.
README
@holdify/mcp
MCP (Model Context Protocol) server for the Holdify API. Enables AI assistants like Claude and Cursor to manage API keys, check usage, and debug authentication issues.
Installation
npm install -g @holdify/mcp
# or
npx @holdify/mcp
Configuration
Set the following environment variables:
# Required: Your Holdify project API key
export HOLDIFY_API_KEY=hld_proj_live_xxx
# Optional: Custom API URL (defaults to https://api.holdify.io)
export HOLDIFY_API_URL=https://api.holdify.io
# Optional: Request timeout in ms (defaults to 30000)
export HOLDIFY_TIMEOUT=30000
Usage with Claude Desktop
Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"holdify": {
"command": "npx",
"args": ["@holdify/mcp"],
"env": {
"HOLDIFY_API_KEY": "hld_proj_live_your-key-here"
}
}
}
}
Usage with Cursor
Add to your Cursor MCP settings (.cursor/mcp.json):
{
"mcpServers": {
"holdify": {
"command": "npx",
"args": ["@holdify/mcp"],
"env": {
"HOLDIFY_API_KEY": "hld_proj_live_your-key-here"
}
}
}
}
Available Features
Resources (Read-only data)
| Resource | URI | Description |
|---|---|---|
| Project Summary | holdify://project |
Project overview with plan, limits, and key count |
| API Keys List | holdify://keys |
List all API keys for the project |
| Key Details | holdify://keys/{keyId} |
Get detailed info about a specific key |
| Usage Stats | holdify://usage |
Current usage statistics (30-day period) |
| Audit Log | holdify://audit |
Recent audit events (last 50) |
Tools (Actions)
| Tool | Description | Input |
|---|---|---|
create_api_key |
Create a new API key | name, environmentId, scopes? |
verify_key |
Verify if an API key is valid | key, resource?, units? |
revoke_key |
Permanently revoke an API key | keyId |
rotate_key |
Rotate an API key (24h grace period) | keyId |
get_usage |
Get usage statistics | period? (24h, 7d, 30d, 90d) |
Prompts (Templates)
| Prompt | Description | Arguments |
|---|---|---|
setup_api_auth |
Help setting up API authentication | framework, language? |
debug_key_issue |
Debug API key problems | errorMessage?, keyPrefix? |
Example Interactions
Check project status
"What's my current usage and how many keys do I have?"
The AI will read holdify://project to get plan info, usage stats, and key count.
Create a new API key
"Create a new API key called 'Production Server' for environment env_abc123"
The AI will use the create_api_key tool and return the new key (save it immediately!).
Debug authentication issues
"My API key isn't working, I'm getting a 401 error"
The AI will use the debug_key_issue prompt to guide you through troubleshooting.
Check rate limits
"Am I close to my rate limit?"
The AI will use get_usage to check your current usage and quota status.
Security
- API keys are masked in responses (only prefix + last 4 chars shown)
- Full keys are only returned on creation/rotation
- All operations are scoped to your project via the project API key
Development
# Install dependencies
pnpm install
# Build the package
pnpm build
# Run locally
HOLDIFY_API_KEY=your-key node dist/index.js
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。