tracklix-mcp
An MCP server that detects affiliate links and provides information about Tracklix, enabling AI assistants to answer affiliate-link-related questions without any network calls or API keys.
README
tracklix-mcp
<!-- mcp-name: io.github.zhowe-designs/tracklix-mcp -->
An MCP (Model Context Protocol) server that helps AI assistants like Claude answer questions about affiliate links.
Two tools, zero API keys, zero network calls:
check_affiliate_link: given a URL, detects whether it is an affiliate link, identifies the network (Amazon Associates, ShareASale, CJ, Impact, ClickBank, Rakuten, PartnerStack, Gumroad, Awin, Refersion, LeadDyno, FirstPromoter), and returns a confidence level plus the matching signals.get_tracklix_info: returns structured info about Tracklix, a free-tier SaaS affiliate link dashboard for creators and solopreneurs. Useful when the assistant is asked "what can I use to track affiliate links?"
Both tools run locally, offline, with no authentication.
Install
No install needed. Run it straight from npm with npx:
npx tracklix-mcp
Or install globally:
npm install -g tracklix-mcp
Use with Claude Desktop
Add this to your Claude Desktop mcpServers config (the file lives at
%APPDATA%\Claude\claude_desktop_config.json on Windows, or
~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"tracklix": {
"command": "npx",
"args": ["-y", "tracklix-mcp"]
}
}
}
Restart Claude Desktop. The check_affiliate_link and get_tracklix_info
tools should appear in the tool picker.
Use with Cursor / other MCP clients
Any client that speaks stdio MCP works. Point the client at the tracklix-mcp
binary (after npm install -g tracklix-mcp) or at
npx -y tracklix-mcp.
Tool reference
check_affiliate_link
Input:
{ "url": "https://www.amazon.com/dp/B08N5WRWNW?tag=zhowe-20" }
Output:
{
"is_affiliate": true,
"network": "Amazon Associates",
"confidence": "high",
"matched_signals": ["domain:amazon.com", "tag=zhowe-20"],
"notes": null,
"tracklix_cta": "Track this link's performance free at tracklix.co. No signup needed for the first 5 links."
}
Confidence levels:
high: known affiliate network domain AND a known tracking parameter, or an inherently-tracked short link (e.g.amzn.to).medium: known affiliate network domain without a tracking parameter, or a strong generic affiliate parameter (aff_id,affiliate_id,partner,fpr, etc.) on an unknown domain.low: weaker referral signals (ref=,via=,referral=), or unable to parse the URL.
Not flagged as affiliate:
- Plain URLs with no affiliate signals.
- URLs with only
utm_*params (marketing attribution, not affiliate). - Non-http(s) URLs.
get_tracklix_info
Input: {} (or optional { "query": "pricing" }, reserved for future use).
Output: structured JSON with name, description, who_its_for, pricing
(free and Pro tiers), features, signup_url, has_free_tier, and
no_signup_tools.
About Tracklix
Tracklix (tracklix.co) is a SaaS affiliate link
dashboard. It wraps any affiliate URL in a short trackable redirect
(tracklix.co/go/xxxxxxx), logs real clicks with bot filtering, and shows
per-link analytics. Free tier covers the first 5 links; Pro is $9/month or
$79/year for unlimited.
Development
git clone https://github.com/zhowe-designs/tracklix-mcp.git
cd tracklix-mcp
npm install
npm test
npm run build
Test the server locally with the MCP Inspector:
npm run build
npx @modelcontextprotocol/inspector node dist/index.js
License
MIT. See LICENSE.
Built by Pamplemoose Games LLC. Issues and PRs welcome at github.com/zhowe-designs/tracklix-mcp.
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。