Mcp Linkedin Post Engager Capture

com.mambabuilt由 mambabuilt.com 发布v1.4.1更新于 Nov 7, 2026

Collect the LinkedIn posts a search engine has indexed for profiles and company pages.

概览

AI 生成的概览

封装 Apify actor,按指定个人主页或公司页面返回搜索引擎已收录的 LinkedIn 帖子,以扁平行形式输出。

可以做什么
  • 采集 LinkedIn 个人主页与公司页面被索引的帖子
  • 每篇帖子返回一行:链接、作者、正文摘录和发布日期
  • 可按 posted_since 日期过滤,并用 max_charge_usd 限制花费
  • 结果中同时返回运行级与来源级的提示行
适用场景
适合想快速获取特定人物或公司公开可被索引的 LinkedIn 帖子、又不想登录 LinkedIn 的场景。它不是完整存档,覆盖范围取决于搜索引擎索引内容。
运行要求
通过 npx(Node.js)以 stdio 在本地运行。需要 Apify 账号和 APIFY_TOKEN 环境变量,并需能访问 Apify 网络;不使用 LinkedIn 账号或 Cookie。
安装前请注意
按采集的帖子数量计费,另加少量 actor 启动费,运行会产生费用,建议设置 max_charge_usd 和 posted_since 控制支出。结果包含具名个人的个人数据,README 说明你为数据控制者。该 actor 为非官方,与 LinkedIn 无关联,且覆盖并不完整。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Mcp Linkedin Post Engager Capture,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

LinkedIn Post Tracker MCP Server

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

[LinkedIn Post Engager Capture MCP server]

MCP server for the Mamba Labs LinkedIn Post Tracker actor on Apify.

Point it at LinkedIn person profiles or company pages. It returns the posts a search engine has indexed for each one, as flat rows: permalink, author, a text excerpt, and the publish date. No request is sent to LinkedIn, and no cookie, account, or credential is used.

Changed in 1.3.0. The actor stopped fetching linkedin.com on 2026-10-12. Commenter rows, reaction and comment counts, media, and the inputs collect_commenters, collect_reactors, max_engagers_per_post, and use_residential_proxy are gone. Posts now come from search results, so coverage is what the index holds: posts appear days or weeks after publishing, and many never appear. The tool keeps its name, capture_linkedin_posts_and_commenters, so existing clients keep working.

Install

bash
npx -y @mambalabsdev/mcp-linkedin-post-engager-capture

Claude Desktop

json
{  "mcpServers": {    "mamba-linkedin-post-engager-capture": {      "command": "npx",      "args": ["-y", "@mambalabsdev/mcp-linkedin-post-engager-capture"],      "env": { "APIFY_TOKEN": "your-apify-token" }    }  }}

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

Tool

capture_linkedin_posts_and_commenters

LinkedIn profiles and company pages in, the posts a search engine has indexed for them out.

InputTypeRequiredMeaning
profile_urlsarray of stringsone of the twoPerson profiles, for example https://www.linkedin.com/in/williamhgates.
company_urlsarray of stringsone of the twoCompany pages, for example https://www.linkedin.com/company/microsoft.
posted_sincestringnoISO date. Posts published before this are skipped before anything is charged.
max_charge_usdnumbernoSpend cap for the run, in USD. The run starts no post whose charge would cross it and writes one max_charge_reached notice row.

Reading the output

  • post is one row per indexed post: post_id, post_permalink, author_name, author_url, author_type, post_text (the search engine's excerpt), published_at (decoded from the post id).
  • notice is a run-level or source-level message. Filter these out before loading a table.

A post counts only when its permalink names the source, for example linkedin.com/posts/stripe_... for linkedin.com/company/stripe. A refused search comes back as a degraded notice, never as "no posts".

Billing

You are charged per post collected, plus a small actor start fee. Notice rows are free. posted_since filters before anything is charged.

EventPrice per event (USD)Fires when
apify-actor-start$0.00005Charged when the Actor starts running, one event per GB of memory.
post-collected$0.002 on the Free plan, down to $0.0017 on higher Apify plansOne LinkedIn post returned from search results, with its permalink, author, text excerpt and publish date.

The actor's Apify page carries the current prices.

What this server does and does not do

It is a thin client for the Apify actor. It passes your input through and returns the actor's output unchanged. Every behavior described above lives in the actor, not here.

It reads only public search engine results. It sends no request to LinkedIn, holds no session cookie, and uses no LinkedIn account.

Post rows from a person profile name that person. When you run this you are the data controller for the personal data it returns and Apify is the processor. Your lawful basis is yours to establish; nothing here is legal advice.

This actor is unofficial and is not affiliated with, sponsored by or endorsed by LinkedIn or Microsoft.

Errors are surfaced, never swallowed. An invalid input, an invalid token, an exhausted balance, a timeout, or a run that returns anything other than a dataset all come back as an explicit tool error rather than as an empty result.

Source

The actor is on the Apify Store. This wrapper is MIT licensed.

Built by Mamba Labs

来源:README.md,提交 9fe4d93

工具

1

capture_linkedin_posts_and_commenters

Capture LinkedIn Posts and Commenters

Point it at LinkedIn person profiles or company pages and it returns the posts a search engine has indexed for each one, as flat rows: permalink, author, a text excerpt, and the publish date decoded from the post id. No request is sent to LinkedIn and no cookie or account is used. A result counts only when its permalink names the source, so posts are never attributed to the wrong author. Coverage is what the search index holds: posts appear days or weeks after publishing and many never appear. Commenters, reaction counts, comment counts and media are no longer returned (removed 2026-10-12, they came only from LinkedIn pages). Rows carry row_type post or notice; filter on row_type before loading a table. post_id is the activity URN and is stable across runs. Every row carries degraded and degradation_reason. Requires an APIFY_TOKEN and consumes Apify credits. Read only.

输入参数company_urlsposted_sinceprofile_urlsmax_charge_usd

版本历史

7
  1. v1.4.1最新Nov 5, 2026
  2. v1.4.0Oct 16, 2026
  3. v1.3.1Oct 16, 2026
  4. v1.3.0Oct 12, 2026
  5. v1.2.1Oct 6, 2026
  6. v1.2.0Oct 6, 2026
  7. v1.1.0Sep 16, 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