LinkedIn MCP (by TalkToHumans)

io.github.CoolSapiens由 GitHub 帳號 CoolSapiens 發布v1.1.0更新於 Oct 24, 2026

The safest LinkedIn MCP: your Agents read DMs, search your network and draft messages you send.

已驗證Streamable HTTP可網頁執行效率與工作流溝通與協作商業與電商

概覽

AI 產生的概覽

託管式 LinkedIn MCP，讓助理讀取你的對話、搜尋人脈、補齊聯絡人資料，並草擬由你親自送出的訊息。

可以做什麼
  • 讀取帳號、對話與訊息，儲存、暫存或清除訊息草稿（不會送出）
  • 搜尋、匯入、更新、標記與刪除聯絡人，並列出公司
  • 搜尋、匯入與追蹤貼文和內容，包括曾互動的人
  • 補齊個人檔案的工作信箱與手機號碼，並管理已儲存的檢視
  • 管理範本與跟進序列，檢視活動摘要
適用情境
適合創辦人、顧問、業務團隊與代理商，讓助理整理 LinkedIn 與 Sales Navigator 收件匣、依理想客戶輪廓為聯絡人評分，並準備待人工確認的回覆與跟進。
執行需求
遠端 Streamable HTTP 端點，以 OAuth 登入 TalkToHumans 帳號，無需本機安裝。MCP 存取需付費的 TalkToHumans 方案，工作區同步需保持瀏覽器擴充功能開啟。部分用戶端需管理員允許自訂連接器。
安裝前請注意
助理可讀取私人訊息與聯絡人資料，並可刪除聯絡人、標籤與序列。匯入、搜尋、資料補齊與追蹤會消耗 TalkToHumans 點數，產生費用。資料補齊會把聯絡人資料傳送給第三方資料供應商。草稿不會自動送出，但刪除類操作仍須確認。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 LinkedIn MCP (by TalkToHumans)，將其新增到工作區。
  2. 連接 所需的 憑證。它們會被私密儲存，絕不會在公開頁面上展示。
  3. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.CoolSapiens%2Flinkedin-mcp/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。 客戶端會在首次連接時完成 OAuth 登入。

{
  "mcpServers": {
    "linkedin-by-talktohumans": {
      "type": "http",
      "url": "https://api.talktohumans.app/mcp"
    }
  }
}

README

[LinkedIn MCP server by TalkToHumans: connect Claude, ChatGPT, Codex, Cursor and n8n to your LinkedIn inbox, network, leads and activity]

LinkedIn MCP Server

The safest LinkedIn MCP for your Agents.

Connect Claude, ChatGPT, Claude Code, Codex, Cursor, VS Code or any remote MCP client to your own LinkedIn account.

Your agent reads your LinkedIn conversations, searches your network, enriches profiles with email and phone, and drafts the messages. You review them and hit send.

[Website] [Docs] [MCP Registry] [Transport] [smithery badge]

[LinkedIn MCP (by TalkToHumans) MCP connector – tool definition quality and endpoint health on Glama]

txt
https://api.talktohumans.app/mcp

Why this LinkedIn MCP is safer

LinkedIn has no official MCP server, and its public API doesn't give access to your private messages. Every LinkedIn MCP is third-party, and most fall into one of three groups:

Open-source scrapersCloud LinkedIn toolsTalkToHumans
PaceWhatever pace your agent setsDaily caps sized for campaignsHuman pace, enforced: daily limits plus a gap between every action, per LinkedIn account. Nobody can override them
What 100 agent calls do100 trips to LinkedIn100 trips to LinkedIn, from their serversRead a synced cache, so no more LinkedIn activity than one call
Where LinkedIn actions runA script driving a browser on your machineTheir servers, often behind proxy IPsThe browser you already use. No cloud automation, no proxy IP
Where you workIn your agent's chatIn your agent's chatWherever suits the task: your agent's chat, the TalkToHumans app, or right inside LinkedIn and Sales Navigator
Who presses sendUsually the agentThe agent or a campaignYou. The MCP only drafts

No LinkedIn tool is completely risk-free. Here is how TalkToHumans keeps the risk down:

  • Human pace, enforced. Every action type has its own conservative daily limit and a slightly random gap between actions, so nothing goes out in bursts. Limits belong to the LinkedIn account, so every teammate and every agent shares them. Nobody can raise them, not even your agent.
  • Cache-based sync. Your agent reads a synced copy of your LinkedIn data, not LinkedIn itself. Ask it 100 questions about your inbox and your account sees the same activity as one, with no hopping from profile to profile. The background sync that fills that copy is paced the same way.
  • Posts and searches skip your account. Posts, comments, the people engaging with them and people searches come from a data provider, never from your LinkedIn session.
  • Runs in your browser. LinkedIn actions go through the browser you already use. No cloud automation, no proxy IPs and no virtual browsers acting on your behalf.
  • Work in the chat, the app or LinkedIn. Everything your agent does also lands in the TalkToHumans app and in panels embedded in LinkedIn's own pages. Check conversations, see what's scheduled and take over by hand wherever you are.
  • Drafts only. The MCP can write a reply or stage a full follow-up sequence. Nothing goes out until you hit send.

What your agent can do on LinkedIn

Founders, consultants, sales teams and agencies use it for the same handful of jobs:

  • Find leads in your network. Describe your ideal customer, and your agent scores your connections. They're already connected to you, so you can message them today.
  • Find the replies you owe. Scan hundreds of LinkedIn, Sales Navigator and Recruiter threads for the ones where someone is waiting on you, every morning if you like.
  • Draft messages in your voice. Your agent researches each person and writes a first message that sounds like you. You review every draft and send it yourself.
  • See what gets replies. Analyze acceptance rates, reply rates and templates, from connection request to booked meeting.
  • Stage follow-up sequences. Follow-ups that stop when the lead replies, written for each person, waiting for you to launch them.
  • Import new leads. Search LinkedIn by role, company or location, or bring in a list from an event or Sales Navigator, and get a ready-to-work view.
  • Mine post comments. Find posts on a topic or by a competitor, and import the people who commented or reacted, each with a signal saying how.
  • Score and tag contacts. Fill an ICP score for every contact, or backfill tags on hundreds of conversations the way your team already uses them.
  • Keep your CRM in sync. Combine it with your CRM's MCP to log LinkedIn conversations, or use the native HubSpot integration.

Your agent also gets work email and mobile phone for the people you talk to, from 20+ providers in a waterfall.

Connect your AI client to LinkedIn

Claude

Click this link to add TalkToHumans to Claude

Click Add, then Connect, and sign in to TalkToHumans.

On Team and Enterprise plans, only an owner can add it: add it as an owner.

Members then click Connect in Customize > Connectors.

Not showing in a chat? Click + > Connectors and turn TalkToHumans on.

Add it by hand
  1. Open Customize > Connectors, click + Add > Add custom connector
  2. Name it "TalkToHumans" and paste the URL:
text
https://api.talktohumans.app/mcp
  1. Click Add, then Connect, and sign in to TalkToHumans

ChatGPT

  1. Open ChatGPT plugins, click + and choose Add custom MCP server
  2. Name it "TalkToHumans" and paste the URL:
text
https://api.talktohumans.app/mcp
  1. Choose OAuth, click Create, then sign in to TalkToHumans

Custom MCP servers depend on your ChatGPT plan. On Business, Enterprise and Edu, an admin may need to allow them.

Claude Code

In a terminal, run:

bash
claude mcp add --transport http --scope user talktohumans https://api.talktohumans.app/mcp

Then run /mcp in Claude Code, pick talktohumans and choose Authenticate.

Already connected Claude? It shows up in Claude Code with the same account.

Codex

In a terminal, run:

bash
codex mcp add talktohumans --url https://api.talktohumans.app/mcp

If no browser opened to sign in, run:

bash
codex mcp login talktohumans

The Codex app and IDE extension share this setup. In the ChatGPT desktop app, add it in Settings > MCP servers.

Cursor

Click this link to add TalkToHumans to Cursor

Add it by hand

Add this to ~/.cursor/mcp.json:

json
{  "mcpServers": {    "talktohumans": {      "url": "https://api.talktohumans.app/mcp"    }  }}

VS Code

Click this link to add TalkToHumans to VS Code

Add it by hand
  1. Open the Command Palette and run MCP: Add Server
  2. Choose HTTP and paste the URL:
text
https://api.talktohumans.app/mcp
  1. Name it talktohumans, choose Global, and sign in when VS Code asks

Gemini CLI

In a terminal, run:

bash
gemini mcp add --transport http talktohumans https://api.talktohumans.app/mcp

Then run /mcp auth talktohumans in Gemini CLI.

Grok

  1. On grok.com, open Connectors, then New Connector > Custom
  2. Paste the URL, then sign in to TalkToHumans:
text
https://api.talktohumans.app/mcp

Perplexity

  1. On Perplexity, open Connectors, then Add custom > Remote MCP
  2. Paste the URL, choose OAuth and Streamable HTTP:
text
https://api.talktohumans.app/mcp
  1. Sign in to TalkToHumans

Custom connectors need Perplexity Pro, Max or Enterprise.

Le Chat

  1. In Le Chat connections, click Add connector, then Custom MCP
  2. Paste the URL, then sign in to TalkToHumans:
text
https://api.talktohumans.app/mcp

Other

Add a custom MCP server (Streamable HTTP, OAuth) with this URL, then sign in:

text
https://api.talktohumans.app/mcp

LinkedIn MCP tools

AreaTools
Accountslist_accounts, get_credit_balance
Conversationslist_conversations, list_messages, write_message_draft, upload_file
Contactslist_contacts, search_people, import_contacts, get_import_progress, update_contact, delete_contacts, list_field_definitions, create_field_definition, list_tags, update_tag, delete_tag, create_signals
Companieslist_companies
Contentlist_content, search_posts, find_content, import_content, import_content_engagers, track_content, update_content
Enrichmentenrich_profile, find_email, find_phone
Viewslist_views, create_view, update_view
Templates & sequenceslist_templates, create_template, update_template, update_sequence, delete_sequence
Reportinglist_activity, get_activity_summary
Skillsload_skill
Feedbacksend_feedback

write_message_draft saves a draft, a sequence or a connection request for you to review, or clears one. It never sends. Imports, searches, enrichment and tracking use TalkToHumans credits. list_accounts also gives your agent your own LinkedIn profile, for free, so it knows who you are.

FAQ

What is a LinkedIn MCP server?

MCP (Model Context Protocol) is the open standard that lets AI assistants like Claude, ChatGPT and Cursor use outside tools. A LinkedIn MCP server connects your agent to your LinkedIn data. It can read your conversations, search your network and prepare messages, instead of you copying everything into a chat.

Is there an official LinkedIn MCP?

No. LinkedIn doesn't offer an MCP server, and its public API doesn't cover private messages. Every LinkedIn MCP is third-party.

Can my agent send LinkedIn messages on its own?

No, and that's on purpose. Your agent can read, sort and draft, down to a full follow-up sequence. Every message that carries your name still gets your approval.

Do I have to give you my LinkedIn password?

No. TalkToHumans works through your logged-in browser session. Your AI client signs in to TalkToHumans, not to LinkedIn.

How fresh is the data?

Your workspace syncs while your browser is open with the TalkToHumans extension on, newest conversations first. Older message history loads when you open a conversation in TalkToHumans.

Is there a LinkedIn CLI?

Yes. The LinkedIn CLI (tth) is the same workspace from the terminal, for Claude Code, Codex, scripts and cron jobs. It only drafts too. See the CLI docs.

Is there a LinkedIn API too?

Yes. Every paid plan also includes a REST API for contacts, companies, conversations, content, drafts, views and activity. See the developer docs.

Which plan includes the MCP?

MCP, CLI and API access come with every paid plan, from Starter. Pro adds sequences, post engagers, analytics and CRM integrations.

About this repository

This repo holds the MCP Registry entry (server.json) and setup docs for the hosted TalkToHumans server. The server runs at https://api.talktohumans.app/mcp, and its code isn't in this repo.

Found a bug or a missing tool? Open an issue.

Built by TalkToHumans.

來源：README.md，提交 e22b7e1

工具

0
該伺服器需要登入，因此 SourceWeft 無法在沒有帳號的情況下讀取其工具，也未收錄。已連接帳號所能看到的內容可能因帳號及其權限而異。

版本歷史

2
  1. v1.1.0最新Oct 23, 2026
  2. v1.0.0Sep 16, 2026

評分

已滿足適用檢查項的 85%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list，或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分