Codinfy MCP

Codinfy MCP

MCP server that connects AI agents to Codinfy platform APIs for validating licenses, creating checkouts, listing products, tracking analytics, managing OAuth identity, and handling ad placements.

Category
访问服务器

README

@codinfy/mcp — Codinfy Public MCP Server

Official Model Context Protocol server for Codinfy. Connect your AI agent (Claude Code, Codex, Cursor, Continue, Cline, Windsurf) to the Codinfy platform to validate licenses, create checkouts, list products, track events, fetch brand tokens, manage OAuth metadata, configure ads, and more.

npm version License: MIT


Status

🚧 v0.1.0 — scaffold. Tool implementations land in AGENT-44. Track progress at docs.codinfy.com/mcp.


What is this?

The Model Context Protocol (MCP) is an open standard that lets AI agents call external tools through a well-defined transport. This package implements the public Codinfy MCP server: a thin TypeScript layer that exposes Codinfy's public APIs as MCP tools.

It is the tool any third-party developer, vendor, or agency uses when they want their agent to talk to Codinfy.

Companion projects

Repo Purpose License
codinfy-mcp (this) Public MCP for Codinfy API consumers MIT
codix-build-mcp Codix Build MCP — scaffold projects with AI agents using Smart Context Mode MIT
codinfy-mcp-internal Private MCP for Codinfy team agents only proprietary

Install

npm install -g @codinfy/mcp
# or
npx -y @codinfy/mcp

Configure your agent

Claude Code / Claude Desktop

~/.claude/mcp.json (or claude_desktop_config.json):

{
  "mcpServers": {
    "codinfy": {
      "command": "npx",
      "args": ["-y", "@codinfy/mcp"],
      "env": {
        "CODINFY_API_KEY": "pk_live_xxxxxxxxxxxxxxxxx"
      }
    }
  }
}

Cursor

Settings → Cursor → MCP → New Server:

{
  "name": "codinfy",
  "command": "npx",
  "args": ["-y", "@codinfy/mcp"],
  "env": { "CODINFY_API_KEY": "pk_live_xxxxxxxxxxxxxxxxx" }
}

Codex / Continue / Cline / Windsurf

See docs.codinfy.com/mcp/clients.


Get an API key

Log in at codinfy.com/admin/parametres/api-s and create a key:

  • pk_live_… — production
  • pk_sandbox_… — sandbox (free tier, rate-limited)

Keys are scoped (licenses:read, payments:write, brand:read, …) and rotateable from the same UI.


Tools (16 — to be implemented in AGENT-44)

Licenses

  • codinfy_license_validate — validate a purchase code and domain
  • codinfy_license_list — list licenses for a customer

Products & checkout

  • codinfy_products_list
  • codinfy_checkout_create
  • codinfy_checkout_status

Brand & design

  • codinfy_brand_get — current site name, colors, logos, social
  • codinfy_brand_tokens_get — Tailwind CSS 4 tokens

Identity (Login with Codinfy — OAuth 2.0 / OIDC)

  • codinfy_oauth_metadata — .well-known/openid-configuration
  • codinfy_oauth_jwks — public JWKS
  • codinfy_oauth_apps_list — list connected applications

Ads

  • codinfy_ads_config_get
  • codinfy_ads_placement_create
  • codinfy_ads_stats_get

Analytics & misc

  • codinfy_event_track — track a custom event
  • codinfy_webhook_test
  • codinfy_health

Detailed schemas, parameters, examples and changelogs live in docs.codinfy.com/mcp.


Development

git clone https://github.com/bakalagoin/codinfy-mcp.git
cd codinfy-mcp
npm install
npm run build
npm test

Project layout

codinfy-mcp/
├── src/
│   ├── index.ts              # MCP server bootstrap (stdio transport)
│   ├── tools/                # one file per tool, all re-exported from index
│   ├── client/               # thin HTTP client for api.codinfy.com
│   └── types/                # shared schemas (Zod)
├── tests/
├── package.json
├── tsconfig.json
└── .github/workflows/        # ci.yml + publish-npm.yml

Releases

Pushing a tag v* to main publishes to npm automatically (see publish-npm.yml).

npm version patch        # 0.1.0 → 0.1.1
git push --follow-tags

Security

Report vulnerabilities privately to security@codinfy.com. See SECURITY.md.

Contributing

Issues and PRs welcome. See CONTRIBUTING.md.

License

MIT © 2026 RAFLOX SAS — Abidjan, Côte d'Ivoire.

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