Intentlink

io.github.whalefuntech由 GitHub 账号 whalefuntech 发布v1.0.0更新于 Oct 27, 2026

The best agent monetization tool: free search, clear rev-share, 10M+ commerce/travel/local offers.

已验证Streamable HTTP可网页运行位置与生活商业与电商

概览

AI 生成的概览

IntentLink 是一个远程 MCP 服务器,让助手搜索联盟购物、旅行和活动优惠,并返回可追踪的购买或预订链接。

可以做什么
  • 用自然语言查询搜索购物商品,获得排序后的推荐,可按关键词和商品类型筛选
  • 按城市搜索酒店、机票、套餐、机场接送和租车等旅行优惠,返回可追踪的预订链接
  • 搜索演唱会、体育赛事、剧场等现场票务活动,返回排序后的活动组合
  • 读取旅行城市资源,获取旅行搜索可用的城市取值
适用场景
适合需要把购物者或旅客的需求转化为具体商业推荐并附上可点击链接的场景,也适合运营方希望把联盟归因绑定到自己的 agent ID 时使用。
运行要求
需要一个远程 MCP 端点,无需本地包或运行时。需要从服务商门户获取 agent_id,并在每次工具调用时传入,而不是写在静态配置里。需要能访问该托管端点的网络。
安装前请注意
返回结果是带商业利益的联盟推荐,建议可能受佣金影响;README 说明转化收益中运营方可保留 80%。agent_id 在每次工具调用中传递,归因会回传到该 ID。README 称不存储个人身份信息、仅使用临时对话上下文进行匹配,但用户查询仍会发送给第三方服务。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Intentlink,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.whalefuntech%2Fintentlink/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "intentlink": {
      "type": "http",
      "url": "https://api.intentlink.io/mcp/"
    }
  }
}

README

IntentLink

Monetize your AI agent's conversations — natively, without banners.

IntentLink is a commercial intent network built for the AI agent era. Add the IntentLink MCP server (or REST API) to your agent, and it gains the ability to surface relevant, monetizable commerce recommendations directly inside its answers — not as an ad unit bolted on top, but as part of the conversation itself.

Website · Docs · Developer Dashboard · For Merchants & Partners

Why IntentLink

  • Native to the conversation. Recommendations surface as part of the agent's answer — contextual and relevant, not a banner or pop-up.
  • Zero UX disruption. Your agent stays your agent. No iframes, no forced redirects, no interruption of the conversation flow.
  • You keep 80% of revenue. Transparent rev-share on every converted intent. No upfront fee, no platform fee — IntentLink only earns when you do.
  • Privacy-first by design. No PII is stored. Intent matching runs on transient conversation context only, aligned with GDPR/CCPA.
  • Works with any MCP-compatible runtime — Claude, OpenAI-compatible agents, LangChain, or custom stacks (a language-agnostic REST API is available as a fallback).

Quick Start

Add IntentLink as a remote MCP server:

json
{"mcpServers": {"intentlink": {"url": "https://api.intentlink.io/mcp/"}}}

Your agent_id is passed per tool call, not in the static config — get one at portal.intentlink.io.

Prefer REST? See the full docs for the language-agnostic API.

What it does

Once connected, your agent can match user intent to relevant commercial offers and return a trackable purchase link for the user to complete the transaction — attribution flows back to your agent_id automatically.

About this repo

This repository hosts public documentation and integration resources for IntentLink. The IntentLink MCP server itself is remotely hosted (not distributed as an installable package) — see Quick Start above to connect.

License

MIT — see LICENSE file for details.

来源:README.md,提交 c541e92

工具

3

search_products

Search affiliate shopping products and get ranked recommendations. Only `query` is required — a natural-language description of what the shopper wants (e.g. "a warm waterproof jacket for winter hiking"). Add fields to narrow results: - keywords: exact product terms. Use a SPECIFIC product type ("women running shoes", "stainless steel knife set"), not a bare generic noun ("shoes", "knife") — a generic keyword can surface the wrong audience. Audience/occasion go in `query`. - commerce_l2s: category ids to restrict to (read the `commerce://categories` resource for valid values — that taxonomy is for shopping only). - max_price / min_price: price band (USD). platforms: ["amazon"|"walmart"] (empty=all). - intent: ranking preset — "cheapest" | "best_discount" | "top_rated" | "best_value". - require_commission: only return products that pay a commission (default: server setting, normally on). Pass false to include zero/unknown-commission products. - limit: max results (default 10). `agent_id` is REQUIRED: your registered, active agent id. It is the attribution key and the access key — a missing/blank or unregistered agent_id is rejected (no anonymous use). Returns {count, products:[{offer_id,title,brand,price,rating,...,buy_url,product_url}]}. Each product's `buy_url` is ALREADY the trackable affiliate buy link — hand it to the shopper directly. (`product_url` is the plain product page.) There is no separate resolve/click step.

输入参数limitquery必填intentagent_id必填keywordsmax_pricemin_priceplatformscommerce_l2srequire_commission

search_travel

Search travel offers and get trackable booking links for a given product type + city. REQUIRED: - type: which travel product — one of ["hotel","flights","bundle","airport_transfer","car_rental"]. - city: city name from the supported list — read the `travel://cities` resource for valid values (that city list is for travel only). Pass hotel.state (e.g. "NY") when the city name is ambiguous. - agent_id: your registered, active agent id — the attribution + access key. A missing/blank or unregistered agent_id is rejected (no anonymous use). HOTEL runs a live Trip.com search — pass the `hotel` object with the stay: check_in / check_out (YYYY-MM-DD), rooms, adults, children, state. If those are missing/invalid or the city can't be resolved, you get the hotel default links instead. Other types currently return curated default links (the `hotel` object is ignored for them). Returns {status, reason, message, links:{<type>:[{title, brand, platform, buy_url, product_url, ...}]}}. status is "ok" = a live hotel result; "fallback" = curated default links (see `reason`); "no_results" = nothing available for the type; "error" = the agent_id was rejected. Each `buy_url` is ALREADY the trackable booking link — hand it to the traveler directly. `product_url` is the plain merchant page.

输入参数city必填type必填hotellimitagent_id必填

search_events

Search live ticketing/events (concerts, sports, theater) and get ranked event bundles. Only `query` is required — a natural-language description of what the buyer wants (e.g. "taylor swift concert near LA this summer"). Add fields to narrow results: - keywords: exact terms — performer / team / show / venue (a precise lookup). - categories: e.g. ["Concerts"|"Sports"|"Theater"] (read the `events://categories` resource for valid values). - city / state: location (e.g. city="Los Angeles", state="CA"). country defaults to US. - date_from / date_to: explicit date window, YYYY-MM-DD (event dates are date-only). - when: fuzzy time — "this_weekend" | "this_week" | "this_month" | "next_7_days" | "next_30_days" (ignored if date_from/date_to are given). - min_price / max_price: ticket 'from' price band (USD). - sort: "relevance" (default) | "soonest" | "cheapest". - limit: max results (default 10). `agent_id` is REQUIRED: your registered, active agent id — the attribution + access key. A missing/blank or unregistered agent_id is rejected (no anonymous use). Returns {count, message, events:[{bundle_id,title,venue,city,next_date,price_min,..., sessions:[{date,price,buy_url,landing_url}]}]}. Each session's `buy_url` is ALREADY the trackable ticket link — hand it to the buyer directly. `landing_url` is the plain event page. When a date filter is given, `sessions` are the in-window dates.

输入参数citysortwhenlimitquery必填statedate_toagent_id必填keywordsdate_frommax_pricemin_price另有 1 个

版本历史

1
  1. v1.0.0最新Sep 16, 2026

评分

已满足适用检查项的 100%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分