mcpField
L
linkedin-people-search

linkedin-people-search

リモート
alphaosint.comその他0今日更新
リポジトリ公式サイト

linkedin-people-search について

採用、営業候補の調査、連絡先の特定向けに、公開 LinkedIn 検索から人物を探すホスト型 MCP サーバーです。プロフィール情報を追加取得でき、呼び出せる Apify Actor は1つに限定されています。

主な機能

  1. 01氏名、職種、勤務先、学校、地域で検索
  2. 02公開プロフィールURLと見出しを取得
  3. 03職歴と学歴を任意で取得
  4. 04キーワードによる結果の絞り込み
  5. 05実行状況の確認と出力のページ取得

活用シーン

  1. 01職種と勤務先で営業候補リストを作成
  2. 02プロフィールURLが不明な候補者を検索
  3. 03企業の連絡先候補を特定

MCP 対応

Apifyのホスト型 MCP エンドポイントを通じて、専用の LinkedIn 検索ツールを公開します。呼び出しでは利用者自身の Apify アカウントで連携する Actor が実行されます。

設定

リモートサーバーはインストール不要です。クライアントを選んで設定をコピーするか、ワンクリックで導入できます。

エンドポイントhttps://mcp.apify.com/?tools=johnvc/linkedin-people-search-api
インストールコマンドをコピー
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

コマンドはターミナルで実行し、JSON は各クライアントの MCP 設定に貼り付けて再起動します。認可が必要なサーバーは初回接続時にログインを求めます。

ツール

README(原文)English

プロジェクトの README より

この README の日本語訳はまだありません。以下は英語の原文です。日本語の紹介はページ上部をご覧ください。

LinkedIn People Search MCP server

Registry name: io.github.johnisanerd/linkedin-people-search. Maintained by AlphaOSINT (Apify developer johnvc, GitHub johnisanerd).

What it does

Find people by name, job title, employer, school or location and get profile URL, headline, current employer, location, and optionally about text, work history and education.

When to use it

Finds people you don't have profile links for yet, where profile tools need the URL first. Use it for prospect lists, recruiting searches and finding the right contact at a company.

How it works

The server runs on Apify's hosted MCP endpoint, so there is nothing to install or host. Its URL pins one Actor with ?tools=johnvc/linkedin-people-search-api, which gives your agent a single tool, johnvc--linkedin-people-search-api, whose parameters are the Actor's typed input schema. The agent can call that tool directly without searching for an Actor first, and it can't start other Actors through this server. For general access to the whole Apify Store, use https://mcp.apify.com without the tools parameter.

Pricing

Each tool call runs the Apify Actor johnvc/linkedin-people-search-api on your own Apify account and is billed there at the Actor's prices:

ChargePrice (USD)What it covers
Person found$0.0006Fee per person delivered to the dataset, with their public LinkedIn profile URL, name, headline and current employer. Charged once per person, never per search page, and never twice for the same person in one run.
Person enriched$0.0025Fee per person whose public profile page was opened and parsed, adding the about text, work history, education, follower count, photo and languages. Charged only when the enrichment actually returned data.

Free-plan rates as of 2026-11-13; paid Apify plans pay less per event. Apify also bills a token amount per run start and stored row ($0.00001, $0.00001). Current prices are on the Actor's page: https://apify.com/johnvc/linkedin-people-search-api

Endpoint

  • Transport: Streamable HTTP
  • URL: https://mcp.apify.com/?tools=johnvc/linkedin-people-search-api
  • Auth: Apify OAuth (opens on first use), or the header Authorization: Bearer <APIFY_TOKEN> (Apify Console → Settings → API & Integrations)

Setup

Claude Code

claude mcp add --transport http linkedin-people-search "https://mcp.apify.com/?tools=johnvc/linkedin-people-search-api"

VS Code (.vscode/mcp.json)

{
  "servers": {
    "linkedin-people-search": {
      "type": "http",
      "url": "https://mcp.apify.com/?tools=johnvc/linkedin-people-search-api"
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "linkedin-people-search": {
      "url": "https://mcp.apify.com/?tools=johnvc/linkedin-people-search-api"
    }
  }
}

Claude Desktop: Settings → Connectors → Add custom connector, and paste the URL. Older versions without remote connectors can bridge through mcp-remote in claude_desktop_config.json:

{
  "mcpServers": {
    "linkedin-people-search": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.apify.com/?tools=johnvc/linkedin-people-search-api"
      ]
    }
  }
}

Tools

ToolWhat it does
johnvc--linkedin-people-search-apiRuns the Actor with the parameters below and returns the result rows.
get-actor-runStatus of a run the tool started (for long runs).
get-dataset-itemsPages through a run's full output when it is larger than the inline result.
get-key-value-store-recordReads a record a run stored.
abort-actor-runStops a run.

Apify's endpoint adds the four helper tools whenever an Actor tool is loaded.

Parameters of johnvc--linkedin-people-search-api
ParameterTypeRequiredDefaultDescription
firstNamestringFirst name of the person to find, for example Jane. Combined with lastName into an exact-phrase search, so the two together find people by full name. Leave both name fields empty only if you are searching with the keywo…
lastNamestringLast name of the person to find, for example Doe. Combined with firstName into an exact-phrase search.
keywordsstringExtra search terms to add to the query, for example a skill, an employer or an industry word. Use this on its own to search without a specific name, or alongside a name to narrow the matches.
jobTitlestringJob title to require, for example Software Engineer. Only people whose public profile or search snippet mentions this title are returned.
companystringEmployer name to require, for example Microsoft. Matches people whose public profile mentions this company, current or past.
schoolstringSchool or university name to require, for example Stanford University.
locationstringPlace to require, for example San Francisco or United Kingdom. Matched as text against the public profile, so a city, region or country all work.
maxResultsinteger25Stop after delivering this many people. You are charged only for the people actually returned. Each search fetches a full page of ten results at once, so a run returns at least ten people when the query has that many ma…
enrichProfilesbooleantrueWhen enabled, each person's public LinkedIn profile page is opened to add their about text, work history with job titles, education, connection and follower counts, photo and languages. Turn this off for a faster, cheap…
Example

Ask the agent in plain language, or call johnvc--linkedin-people-search-api with arguments such as:

{
  "jobTitle": "CTO",
  "company": "Stripe",
  "maxResults": 10
}
Output

JSON rows with these fields:

FieldTypeDescription
resultTypestring: person, errorRow kind. 'person' is a matched person. 'error' reports a page that could not be read and is never charged.
profileUrlstringCanonical public LinkedIn profile URL, with all tracking parameters removed.
publicIdentifierstringThe profile slug, which is the last path segment of the profile URL. Stable per person and useful as a deduplication key.
fullNamestringThe person's name as shown on their public profile.
headlinestringThe professional headline shown under the person's name, usually their role and employer.
currentCompanystringEmployer the person currently lists first on their profile.
currentCompanyUrlstringLinkedIn company page for the current employer, when the profile links one.
aboutstringThe person's public About/summary text. Present only when the profile was opened for enrichment.
locationLocalitystringCity or metropolitan area from the public profile.
locationCountrystringTwo-letter country code from the public profile.
profilePhotoUrlstringPublic profile photo. Absent when the person has no public photo.
followerCountintegerNumber of followers shown on the public profile.
experiencearrayPositions listed on the public profile, most recent first. Each entry has organizationName, organizationUrl, organizationLocation, role, startDate and endDate where the profile shows them.
educationarraySchools listed on the public profile. Each entry has organizationName, organizationUrl, startDate and endDate where shown.
languagesarrayLanguages listed on the public profile.
awardsarrayHonours and awards listed on the public profile.
isEnrichedbooleanTrue when the person's public profile page was opened and parsed. False when the row carries search-level data only, which happens when enrichment is off or the profile would not open.
searchRankintegerPosition of this person in the search results, starting at 1.
searchQuerystringThe exact public search query this run used, so every row can be traced back to what was asked.
searchHeadlinestringThe headline text the search result showed, kept when the opened profile page has its own headline (which then fills headline). Absent on rows that were not enriched, where headline is the search text.
currentTitlestringJob title at the current employer, from the public profile. Each experience entry also carries its own title when the profile shows one.
connectionsintegerConnection count shown on the public profile. LinkedIn caps the display at 500, so 500 means 500 or more; see connectionsText.
connectionsTextstringThe connection count as LinkedIn shows it, for example 500+.
memberIdstringLinkedIn's numeric member id for the profile, when the public page exposes it. Stable even if the profile URL changes.
positionsarrayEvery position in the profile's experience section, past roles included. Each entry has title, companyName, companyUrl, startDate, endDate, duration, location and isCurrent where the profile shows them.
fromCachebooleanTrue when this row was served from the shared result cache instead of a new request: the opened profile for an enriched row, the search page otherwise. Billed like a fresh row. Search result pages are reused for up to 1…
fetchedAtstringUTC time the row's data was fetched from LinkedIn's public pages (the profile page for an enriched row, the search page otherwise). For a cached row this is the original fetch time.
errorTypestringShort error class on error rows: 'SearchUnavailable' when the search could not be served (retry later). Absent on other error rows and on people.
errorMessagestringWhy a page could not be read. Only present on rows where resultType is 'error'.

Data source and terms

Public LinkedIn profiles found through web search and read from their public pages, collected by scraping. No login or cookies are used. The server returns the data as published at the time of the call. You are responsible for using it in line with the source's terms and the laws that apply to you. AlphaOSINT is not affiliated with the source.

Links

コメント

MCP は初めてですか?

プロトコルの概要から最初のサーバーの導入まで、よくある疑問にまとめて答えます。

AI アプリケーションが外部のツールやデータソースに統一的な方法で接続するためのオープンなプロトコルです。クライアントはモデルとの対話を担い、MCP サーバーはツール・リソース・プロンプトテンプレートを提供します。標準メッセージでやり取りするため、1 つのサーバーを複数のクライアントで再利用できます。