random-profiles-mcp

random-profiles-mcp

Enables AI agents to generate fake user profiles and companies using the Random Profiles API with automatic API key handling.

Category
访问服务器

README

random-profiles-mcp

MCP server for the Random Profiles API — generate fake user profiles and companies directly from AI agents like Claude.

Setup — zero config

Just install the MCP server and talk to it. The first time you ask for profiles, the agent will prompt you for an email once, claim a free key on your behalf, cache it locally, and use it for every future request. The key is also emailed to you as a receipt.

Add to your Claude Code MCP config (.mcp.json):

{
  "mcpServers": {
    "random-profiles": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "random-profiles-mcp"]
    }
  }
}

Restart Claude Code and ask "give me 5 random user profiles" — the agent will handle the key handshake automatically. No browser, no copy-paste.

The key is cached at ~/.random-profiles/config.json (mode 0600) so you only do this once per machine.

Prefer to bring your own key?

If you already have an API key (or want to use a specific one for billing), set it via env var and skip the claim flow entirely:

{
  "mcpServers": {
    "random-profiles": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "random-profiles-mcp"],
      "env": {
        "RANDOM_PROFILES_API_KEY": "rp_your_key_here"
      }
    }
  }
}

The env var takes precedence over the cached key.

Tools

Tool Description
claim_api_key Claim a free API key using an email address (response returns the key; the agent also emails a copy as a receipt). Only used on first run when no key is configured — cached afterward.
get_profiles Get random user profiles with filters (count, gender, country, age range, fields)
get_profile Get a single profile by UUID
get_companies Get random fake companies with filters (count, industry, country, size, fields)
get_company Get a single company by UUID
get_random_image Get a random profile photo (JPEG, optional size)
get_image Get a specific profile photo by UUID (JPEG, optional size)
get_usage Check your API key usage, tier, and daily limits

Field Groups

Profiles: name, email, phone, identity, bio, social, physical, job, address, financial, network, documents, vehicle, contact, digital, interests, education, photo, relationships, meta

Companies: name, industry, size, location, contact, social, financial, tech, leadership, legal, operations, product, relationships, meta

The relationships group returns cross-resource UUIDs: profiles have company_uuid + colleague_uuids, companies have employee_uuids. Chain tools together to hydrate the graph (e.g. "give me 5 companies, then their employees").

Image formats

Both get_profiles and get_companies accept an optional photo_format / logo_format argument (jpg or webp). WebP is ~30% smaller than JPG with equivalent perceived quality and is supported by 96%+ of browsers. Default stays jpg for maximum compatibility.

Examples

Profiles

"Give me 5 random US profiles"

"Generate 10 female profiles between ages 25-35 from Germany"

"Get me profiles with only name and email fields"

"Show me a random profile photo"

Companies

"Give me 5 fake Technology companies from the US"

"Generate 10 Healthcare companies with 51-200 employees"

"Get 20 companies with only name, industry, and leadership fields"

"Give me 3 Finance companies from the UK with a fixed seed of 42"

"Give me 10 companies with 128px logos (for an icon grid)"

The logo_size argument on get_companies/get_company picks the size variant in meta.logo_url — same pattern as photo_size on profiles. Valid values: 64, 128, 256, 512, 1024 (default).

Environment Variables

Variable Required Description
RANDOM_PROFILES_API_KEY Yes Your API key (get one at random-profiles.com)

See also

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