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.
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.
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_…— productionpk_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 domaincodinfy_license_list— list licenses for a customer
Products & checkout
codinfy_products_listcodinfy_checkout_createcodinfy_checkout_status
Brand & design
codinfy_brand_get— current site name, colors, logos, socialcodinfy_brand_tokens_get— Tailwind CSS 4 tokens
Identity (Login with Codinfy — OAuth 2.0 / OIDC)
codinfy_oauth_metadata—.well-known/openid-configurationcodinfy_oauth_jwks— public JWKScodinfy_oauth_apps_list— list connected applications
Ads
codinfy_ads_config_getcodinfy_ads_placement_createcodinfy_ads_stats_get
Analytics & misc
codinfy_event_track— track a custom eventcodinfy_webhook_testcodinfy_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
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。