PostcardAI MCP Server

PostcardAI MCP Server

Enables AI assistants to create, design, and send physical postcards directly through the PostcardAI platform. It provides comprehensive tools for managing contacts, generating postcard designs from prompts, and tracking mailing delivery metrics.

Category
访问服务器

README

PostcardAI MCP Server

npm version License: MIT

Model Context Protocol server for PostcardAI. Use PostcardAI with Claude, Cursor, and other AI assistants.

Quick Start

1. Install & Authenticate

npx @postcardai/cli login

This opens your browser to authenticate and stores credentials securely.

2. Configure Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "postcardai": {
      "command": "npx",
      "args": ["-y", "@postcardai/mcp-server"]
    }
  }
}

3. Restart Claude Desktop

That's it! Ask Claude to send postcards.

Alternative: API Key

If you prefer not to use the CLI login:

{
  "mcpServers": {
    "postcardai": {
      "command": "npx",
      "args": ["-y", "@postcardai/mcp-server"],
      "env": {
        "POSTCARDAI_API_KEY": "pcai_sk_live_xxx"
      }
    }
  }
}

Get your API key from https://app.postcard.ai/settings/api

Available Tools

Mailings

Tool Description
create_mailing Create and send a postcard mailing
list_mailings List mailings with filters
get_mailing Get mailing details
cancel_mailing Cancel a pending mailing
get_mailing_previews Get preview images
send_mailing Confirm and send after preview
get_mailing_analytics Get delivery metrics

Contacts

Tool Description
create_contact Create a new contact
create_contacts_batch Batch create (max 1000)
match_contact Find by email/phone/address
list_contacts List with search
get_contact Get details
update_contact Update fields
delete_contact Remove contact
get_contact_history Get mailing history

Designs

Tool Description
create_design Generate from prompt
list_designs List saved designs
get_design Get with iterations
iterate_design Generate variations
publish_design Publish iteration
delete_design Archive design

Lists

Tool Description
create_list Create contact list
list_lists List all lists
get_list Get list details
update_list Update name/description
delete_list Delete list
add_contacts_to_list Add contacts
remove_contacts_from_list Remove contacts

Credits

Tool Description
get_credit_balance Check balance
estimate_mailing_cost Estimate cost
purchase_credits Buy credits
get_credit_transactions Transaction history

Brands & Addresses

Tool Description
create_brand Create brand profile
list_brands List brands
set_default_brand Set default
create_return_address Add return address
set_default_return_address Set default

Account

Tool Description
get_account Organization info, plan, usage

Example Prompts

Once configured, try asking Claude:

  • "Send a postcard to John Smith at 123 Main St, Austin TX 78701 with a summer home buying theme"
  • "Show me my credit balance"
  • "Create a new contact list called 'VIP Clients'"
  • "Generate a thank you postcard design for new customers"

Configuration

Environment Variables

Variable Required Description
POSTCARDAI_API_KEY No API key (alternative to CLI login)
POSTCARDAI_API_URL No API URL (default: https://api.postcard.ai/v1)
POSTCARDAI_CONFIG_PATH No Custom config file path

Credential Priority

  1. POSTCARDAI_API_KEY environment variable
  2. ~/.postcardai/config.json (from CLI login)
  3. Custom path via POSTCARDAI_CONFIG_PATH

Other Clients

Cursor

Add to Cursor settings under MCP:

{
  "postcardai": {
    "command": "npx",
    "args": ["-y", "@postcardai/mcp-server"]
  }
}

Claude Code

claude mcp add postcardai npx @postcardai/mcp-server

Documentation

License

MIT

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选