Mcp Link In Bio Newsletter Checker

com.mambabuilt由 mambabuilt.com 发布v1.2.1更新于 Nov 7, 2026

Follow a creator bio link and report the newsletter, what they sell, and the contact emails.

已验证STDIO仅桌面网页搜索与抓取数据与分析商业与电商

概览

AI 生成的概览

封装 Apify actor，追踪创作者的主页链接，报告其是否运营邮件通讯、销售什么以及联系邮箱。

可以做什么
  • 检查主页链接页：根据账号或链接页 URL 追踪，给出是否运营邮件通讯的结论、托管平台和佐证页面 URL
  • 解析创作者身份：返回链接页托管方、经重定向解析出的自有网站以及所售商品
  • 收集联系方式：可选扫描创作者自有网站查找邮箱，并将经纪人或代理机构邮箱域名与内置机构名单匹配
  • 处理无法读取的页面：可选在无头浏览器中渲染空壳页面，并通过住宅代理重试被拦截的资料页
  • 批量与报告：支持单个创作者或列表，自动去重，每行都返回状态和错误原因
适用场景
适用于网红外联、赞助或合作调研以及线索名单构建，尤其是需要快速判断创作者是否运营邮件通讯并找到联系方式时。它只读取你指定的创作者，不进行搜索。
运行要求
通过 npx 在本地运行，需要 Node.js。需要 Apify 账号和 APIFY_TOKEN 环境变量，底层 actor 在 Apify 上按事件计费。可选附加功能需要自备 Anthropic 或 OpenAI API 密钥，通过 ai_api_key 传入。
安装前请注意
该 actor 在 Apify 上按事件计费：启动、检查链接、浏览器渲染、网站扫描、机构匹配和 Instagram 住宅代理读取都会产生费用，建议设置 max_charge_usd。可选的 ai_api_key 会发送给所选模型服务商。默认情况下运行会把发现的公开记录贡献到共享的创作者与机构池，可将 contribute_to_shared_pool 设为 false 以不写入。它会收集联系邮箱，且不支持 X、Facebook 主页和 LinkedIn。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Mcp Link In Bio Newsletter Checker，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。

Desktop only，通过 STDIO。 STDIO 服务会启动本地进程，因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

Link in Bio Scraper and Newsletter Detector MCP Server

[Glama score] [MCP Registry] [npm version] [npm downloads] [license] [mcpservers.org]

[Link In Bio Newsletter Checker MCP server]

MCP server for the Mamba Labs Link in Bio Scraper and Newsletter Detector actor on Apify.

Creator handles or link in bio URLs in, a newsletter verdict and contact details out.

Install

bash
npx -y @mambalabsdev/mcp-link-in-bio-newsletter-checker

Claude Desktop

json
{  "mcpServers": {    "mamba-link-in-bio-newsletter-checker": {      "command": "npx",      "args": ["-y", "@mambalabsdev/mcp-link-in-bio-newsletter-checker"],      "env": { "APIFY_TOKEN": "your-apify-token" }    }  }}

Get an Apify token at console.apify.com/account/integrations.

Tool

check_link_in_bio_and_newsletter

Follow a creator bio link and report the newsletter, what they sell, and the contact emails.

InputTypeRequiredDescription
handlesarray of stringnoOne per line. A profile URL on any supported platform (https://www.tiktok.com/@name, https://www.instagram.com/name/, https://www.youtube.com/@name, a Pinterest, Twitch, or Threads profile, an Apple Podcasts show page, or a Spotify show), or platform:@handle (tiktok:@name). A bare @handle needs platforms and is looked up on each listed platform. One entry is a single run; a list is a batch. Duplicates are removed before any fetch.
bio_linksarray of stringnoSkip the profile read and start from these pages directly (a Linktree, Stan Store, linkin.bio page, or the creator's own site). One per line. When one input item carries both a handle and bio links, the links are read as that creator's links and the actor returns one row for that creator, not one row per link; to get one row per link, pass the links in bio_links alone.
platformsarray of tiktok, instagram, youtube, pinterest, twitch, threads, podcastnoWhich platforms a bare @handle is looked up on. A full profile URL carries its own platform and ignores this. This actor does not search; pass the creators you want read. Supported: TikTok, Instagram, YouTube, Pinterest, Twitch, Threads, and podcasts. Not X, not Facebook pages, not LinkedIn.
render_unreadable_pagesbooleannoOff by default. Some link-in-bio pages (Stan Store, linkin.bio, Typeform shells) return an empty shell to a plain fetch and are classified unknown_fetch_failed. Turn this on to render them in a headless browser. Charged per page rendered (event browser-render) to cover the browser compute. Default: false.
ai_checkbooleannoOff by default. When on, a model reads the rule classifier's evidence and rules on each row. Runs only with your own key in ai_api_key; the actor never uses a Mamba Labs key and never logs yours. Default: false.
ai_providerone of anthropic, openainoWhich API the key belongs to. Default: "anthropic".
ai_api_keystringnoYour own model API key. Used only when ai_check is on. Never stored, logged, or written to a row.
scan_website_for_emailbooleannoOff by default. For creators with their own website (not a link-in-bio page), reads the home, contact, and about pages and the footer for an email and records where it was found. Charged per creator scanned (event website-scan). Default: false.
match_agenciesbooleannoMatches the domain of a manager or business email against the bundled talent agency list and fills agency_name, agency_domain, and agency_match_method. Charged per matched row (event agency-match). Default: true.
escalate_on_blockbooleannoOn by default. A profile fetch that comes back as a bot detection page is retried once over the residential proxy. On Instagram the bio, bio link, and following are read from the profile page over residential when the embed and the datacenter API did not carry them, and a page that comes back readable charges instagram-bio-fetch ($0.010). Uncheck it to never pay that event: a blocked profile then returns a labeled error row, and Instagram rows keep an empty bio and bio link on about half of the reads. Default: true.
max_residential_readsintegernoCaps how many Instagram profile pages one run reads over the residential proxy (each readable one charges instagram-bio-fetch). 0 means no cap. Once the cap is reached, later Instagram rows keep what the embed widget and the datacenter API returned, and error_reason reads escalation_skipped on the rows that would have escalated. Only acts when escalate_on_block is on. Default: 0.
max_download_mbintegernoThe largest page or file the actor downloads from a creator's links, in megabytes. A link whose Content-Length is over the limit is not downloaded; a link with no Content-Length is read up to the limit, then stopped and discarded. Either way the row comes back with every other field filled and error_reason reads file_too_large, and the rest of the batch is not affected. 1 to 200. Default: 25.
batch_sizeintegernoRows fetched at once. Leave empty for the measured per platform default; the measurement is in the README. Higher is faster and, above the measured point, loses rows.
contribute_to_shared_poolbooleannoOn by default. Contributes the public records this run finds to a shared creator and agency pool that all users of this actor read from, so a later run reads what this one found. Only public data already in the returned rows is sent, never your Apify account, your input list, or your API keys, and a contribution is not charged. Set false to read the pool and write nothing. Default: true.
max_charge_usdnumbernoOptional spending cap for this call, in USD. The actor stops before any charge that would take the run past this amount and keeps every row already charged.

Nothing is required. Link in Bio Scraper and Newsletter Detector answers a run with no usable input with a row carrying row_status and error_reason rather than failing, and the tool mirrors that.

Pricing

Link in Bio Scraper and Newsletter Detector is pay per event on Apify. Every price below is flat across every Apify plan tier, read from the live pricing record on 2026-10-05.

EventCharged forPriceFires when
actor-startActor start$0.002Once per run, on start. Covers the run overhead.
links-checkedLinks checked$0.008Once per creator whose bio link or link-in-bio page was fetched and classified. A creator with no bio link returns newsletter_status none from the bio alone and does not charge this event.
browser-renderBrowser render$0.004Once per page rendered in the headless browser because the plain fetch did not return readable content (Stan Store, linkin.bio, Typeform shells) and the rendered page came back readable: 120 characters of visible text or 3 links off the page's host, and no block page. A render that returns the same empty shell is not charged, and a charged render always reaches the classifier. Only when the option is on. Priced to cover the browser compute.
website-scanWebsite scan$0.005Once per creator whose own website (not a link-in-bio page) was scanned for an email on the home, contact, about, and footer. Only when the add-on is on.
agency-matchAgency match$0.003Once per creator row where a manager or agency email domain was matched against the bundled agency list and an agency name came back.
instagram-bio-fetchInstagram bio fetch$0.01Once per Instagram profile row when the bio, bio link, and following were not on the embed widget or the datacenter API and the profile page was read over the residential proxy and came back readable. Only when escalate_on_block is on. Never on the embed or datacenter reads, never on another platform, never on a blocked page, and never on an error row.

The platform's synthetic apify-actor-start event is not in this actor's pricing record and is not charged: the actor's own actor-start event above covers the run overhead.

Reading the output

Every row carries row_status and error_reason. A creator the actor could not read comes back as a row saying why, not as a gap in the list, so an absence is readable rather than inferred. Filter on row_status before loading a table.

What this actor shares

The run contributes the records it finds to a shared creator and agency pool that all users of this actor read from. What one run finds, the next run can read.

The toggle is contribute_to_shared_pool. It is on by default. Set it to false and the run still reads the pool and writes nothing to it.

What this actor contributes. The manager contacts it finds, the agency it matched them to, and any manager email domain the pool has not seen before, as a candidate agency for a later run to confirm.

Only public data that is already in your own output. Every field written to the pool is a field this run returned to you, read from a page the platform or the creator publishes to anyone without a login. Nothing from your Apify account, your input list, your API keys, or your own notes is sent. A contribution never deletes anything from the pool.

What a contribution is labeled with. The actor ID, the run ID, the pool key issued to the actor build, and a hash of the calling IP address, used for the rate limit and nothing else. Your Apify account and your user ID are not recorded.

Contributing is free. No event is charged for a write to the pool. If the pool is unreachable the run finishes as normal, the rows are dropped, and the run log says so.

Actor

Actor ID OorucdheTIgu7RFzK. The wrapper calls the actor by that immutable ID rather than by its Store slug, so a Store rename never breaks it.

Suite

ActorActor IDMCP server
Influencer FindertpkedmloIIWtXx6sg@mambalabsdev/mcp-creator-finder
Influencer Profile ScraperEqEnklDVMIcB1V499@mambalabsdev/mcp-creator-profile-reader
Link in Bio Scraper and Newsletter DetectorOorucdheTIgu7RFzK@mambalabsdev/mcp-link-in-bio-newsletter-checker
Influencer Change Monitord2VVgahNL6UmcLkhg@mambalabsdev/mcp-creator-change-monitor
Influencer Lead List BuilderKnmByszcv135yM30G@mambalabsdev/mcp-creator-lead-list-all-in-one
Influencer Talent Agency LookupzCuX4Mgyg6JvXgGzd@mambalabsdev/mcp-talent-agency-lookup

Built by Mamba Labs.

来源：README.md，提交 056bf4d

工具

1

版本历史

6
  1. v1.2.1最新Nov 5, 2026
  2. v1.2.0Oct 16, 2026
  3. v1.1.1Oct 6, 2026
  4. v1.1.0Oct 6, 2026
  5. v1.0.1Sep 23, 2026
  6. v1.0.0Sep 22, 2026

评分

已满足适用检查项的 90%

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25 分
  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头，或保持端点能够响应探测，以便判定其认证方式。

  • 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