Profile and company data — read 20 September 2026

Bright Data MCP (LinkedIn tools)

A general web-access server with five LinkedIn extractors: hand it a profile, company, job, post or people-search URL and it returns structured JSON. It holds no LinkedIn credential, so there is no account to restrict. A Bright Data API token. No LinkedIn account, login or cookie is involved.

Vendor API keyLow account riskActive

Source: github.com/brightdata/brightdata-mcp ↗
Last read: 20 September 2026

✓ Read from the repository, not from a directory listing✓ Write actions separated from read actions✓ Status derived from the last code change, not the maintainer's word✓ Every source URL published below

69 tools registered

0 write to LinkedIn

2655 GitHub stars, 20 September 2026

8 clients documented

Where it fits

What it is built for, and the jobs it cannot do

The second card is the one a repository README never contains. Both are written from the project's own documentation and source, read on 20 September 2026.

Use it for

Bulk read-only enrichment where no LinkedIn account should be put at risk: pulling structured profile, company, post, job and people-search JSON from URLs you already have, inside an agent that also needs general web search and scraping.

Do not use it for

Anything that writes to LinkedIn — posting, commenting, reacting, connection requests, messages or InMail. Not for Sales Navigator or Recruiter workflows, not for acting as a specific logged-in person, and not for anyone who needs LinkedIn-only scope: this is a general web-access server of which five tools are LinkedIn extractors.

Publisher: Bright Data — the data-collection vendor, maintaining its own server — the vendor of the product it drives.
Licence: MIT — open source
Version: 2.11.3
Runs: Either
Transport: stdio and Streamable HTTP
Repository: github.com/brightdata/brightdata-mcp
Homepage: brightdata.com/ai/mcp-server/linkedin
Last read: 20 September 2026

Hosting and transport are as the project documents them: A hosted endpoint at mcp.brightdata.com needing no local install, or a local stdio process launched by the client. A Dockerfile is in the repository but is not part of the documented install.

Authentication — the thing that decides everything else

A Bright Data API token. No LinkedIn account, login or cookie is involved.

A third-party data vendor's key. No LinkedIn login, cookie or grant is involved, and the vendor's own infrastructure does the fetching.

What this route cannot do, however well the server is written

No account of yours can be restricted, because no account of yours is used. You are instead paying someone else to do what LinkedIn’s terms forbid, so the exposure is contractual and legal rather than account-level.

Low account risk

No LinkedIn account is behind the server, or it acts only through LinkedIn’s own approved API and only to read. Nothing here can get an account restricted.

What it does with the credential

A Bright Data API token, taken from the account settings of a free or paid Bright Data account. Locally it is passed as the API_TOKEN environment variable; on the hosted server it is a token query parameter on the endpoint URL. You never supply LinkedIn credentials, a session cookie or an OAuth grant.

Account risk is derived from the authentication class and from whether the server writes to LinkedIn — not judged per project. The 5 classes and the rule that maps them are on the LinkedIn MCP server directory; the ceilings LinkedIn enforces on any account, automated or not, are on LinkedIn limits. What this particular server exposes, and what it does with your credentials, is below.

Exposed tools

It reads. It registers no write tool at all

These are the tool names the server registers, as a client sees them. An assistant can call any tool the server exposes once it is connected, so the list below is the whole surface, not a feature summary.

web_data_linkedin_person_profile
web_data_linkedin_company_profile
web_data_linkedin_job_listings
web_data_linkedin_posts
web_data_linkedin_people_search
scraping_browser_navigate
scraping_browser_snapshot
scraping_browser_click_ref
scraping_browser_type_ref
scraping_browser_fill_form
scraping_browser_screenshot
scraping_browser_get_text
scraping_browser_get_html
scraping_browser_scroll
scraping_browser_network_requests

15 of the 69 tools it registers are named above. Five of its tools are LinkedIn extractors; the rest are general web search, scraping and remote-browser control. The list above is the LinkedIn set plus the browser tools most likely to be pointed at LinkedIn.

What it can read

6 read actions, written as what they return rather than as the tool signature.

Read a LinkedIn person profile as structured JSON from a profile URL.
Read a LinkedIn company profile as structured JSON from a company URL.
Read LinkedIn job listings as structured JSON from a jobs URL.
Read a LinkedIn post as structured JSON from a post URL.
Read LinkedIn people-search results as structured JSON from a public people-search URL.
Navigate, snapshot, screenshot and extract text or HTML from any page in a vendor-hosted remote browser.

What it can write, and where the write lands

Nothing. The server registers no write tool of any kind, on LinkedIn or anywhere else.

Setup — easy

Installing it, in the project's own commands

Every command and every configuration block below is the project's own, copied unchanged on 20 September 2026. Where a project publishes no config block, this page says so rather than composing one — a snippet written here would be a snippet the maintainer never tested.

Hosted, nothing to install

Shell

claude mcp add --transport http brightdata "https://mcp.brightdata.com/mcp?token=YOUR_API_TOKEN"

claude mcp add --transport http brightdata "https://mcp.brightdata.com/mcp?token=YOUR_API_TOKEN"

Local

Shell

npx @brightdata/mcp

npx @brightdata/mcp

API_TOKEN goes in the client config env block rather than on the command line.

The configuration block

Client config keys are not interchangeable, and a block pasted under the key a different client expects fails silently rather than erroring. That is why the blocks below are the project's own, in the clients it names, rather than one block normalised here.

Local install with npx

JSON

{
  "mcpServers": {
    "Bright Data": {
      "command": "npx",
      "args": ["@brightdata/mcp"],
      "env": {
        "API_TOKEN": "<your-api-token-here>"
      }
    }
  }
}

{
  "mcpServers": {
    "Bright Data": {
      "command": "npx",
      "args": ["@brightdata/mcp"],
      "env": {
        "API_TOKEN": "<your-api-token-here>"
      }
    }
  }
}

What it needs before it will start

A Bright Data account and API token; the free tier needs no card. For the local install, Node.js and npx — package.json declares no engines field, so no minimum Node version is stated. No Docker required. No local headless browser required: browser automation runs on Bright Data's remote endpoint, and Playwright ships as a client-side dependency to drive it. The hosted endpoint needs no local install at all. Proxy rotation and unblocking are vendor-side.

Clients the project documents

Claude Desktop; Claude Code; Cursor; VS Code; Windsurf; Gemini CLI; Zed; Warp. Where the file goes in each Claude surface. The same block in Cursor.

How it talks to the client

stdio locally, launched by the client through npx; streamable-http for the hosted endpoint, which the VS Code config block declares with a type of "http".

Where the process runs

A hosted endpoint at mcp.brightdata.com needing no local install, or a local stdio process launched by the client. A Dockerfile is in the repository but is not part of the documented install.

What it costs to run

The vendor's own figures, quoted rather than computed

5,000 free requests a month, renewing on the 1st, with no card required; unused requests do not carry over and on team accounts the free tier is shared across every user in the account. Beyond it, pay-as-you-go: the docs quote "Search, Scrape & Extract: $1.50 / 1K results" and "Browser Navigation: $8 / GB". Nothing is charged unless the free tier is exhausted and funds have been deposited, and a spend cap can be set in the control panel. Read from the README and docs.brightdata.com on 20 September 2026.

Sales Navigator — Not supported

No tool accepts a Sales Navigator URL or requires a Sales Navigator seat. The people-search tool takes a public LinkedIn people-search URL.

Recruiter — Not supported

The job tool reads public job-posting pages. There is no access to Recruiter seats, projects, applicant pipelines or InMail.

None of the figures above are LinkedIn's. They are third-party prices in the currency and the tiering each project publishes, read on 20 September 2026 and quoted rather than converted.

Repository signals, read 20 September 2026

The code has moved recently

5 days between the last code change and the day these figures were read. Code changed within 90 days of the day this directory was checked.

How far the project has got

Mature and actively maintained. Created April 2025, 348 commits on main, npm package at 2.11.3, changelog entries dated 15 September, 10 September and 27 July 2026. Vendor-maintained rather than a community side project.

How this status was decided

Active means code changed within 90 days of the observation date; stale means up to 365 days. It is measured from the last change to code, not to the README, and never from the maintainer's own adjective. Anything past a year is dropped from this directory rather than published as dormant.

Stars: 2655 — GitHub API stargazers_count. The repository page rounds it to 2.7k.
Last commit: 15 September 2026 — Latest commit on main. The API pushed_at of 17 September counts pushes to other branches.
Open issues: 13 — The API's open_issues_count of 44 includes open pull requests.
Status: Active
Observed: 20 September 2026

Every figure in this section was read from GitHub on 20 September 2026, and star and issue counts move daily. The issue count is the Issues tab, not the API field of the same name — that one counts pull requests as issues and overstates every repository in this directory.

Credential handling and known problems

What to check before you point it at a real account

Both cards below are read from the repository and its own security documentation. A project saying what it does with a session is evidence of intent, not proof of behaviour.

What running it exposes

No LinkedIn account risk of the usual kind: the server holds no LinkedIn credential, so there is no session to restrict or ban. Data is collected through the vendor's proxy network with bot detection and CAPTCHA handling on their side, which is scraping of LinkedIn against LinkedIn's terms regardless of who performs it — the exposure is legal and contractual rather than account-level. The remote-browser tools can click, type and fill forms, so a determined operator could drive an interactive session by hand, but no tool logs in anywhere and none targets a LinkedIn write endpoint.

How it handles your credentials

The API token is a plaintext secret in the client config, or in the hosted endpoint's query string where it can land in logs and shell history. Two recent releases were security hardening: 2.11.3 redacts credentials embedded in URLs from error output, and 2.11.2 stopped a batch tool from returning raw error objects. Every request and the resulting page content passes through Bright Data's infrastructure.

2 things that will waste an hour

Small, checkable and specific to this project — a stale package name, a broken link, a manifest that advertises something the code removed.

package.json declares no engines field, so the project states no minimum Node version.
On a team account the 5,000-request free tier is shared across every user in the account, not granted per user.

If this is not the one

The servers that do a comparable job, and how they differ

Same rows, same sources, same observation date. The first column is this server.

Bright Data MCP (LinkedIn tools) compared with its alternatives
	Bright Data MCP (LinkedIn tools)v2.11.3	Anysite MCP Serverv3.0.0	Insaightv0.1.0
Authenticates with	Vendor API key	Vendor API key	Vendor API key
Account risk	Low	Low	Low
Writes to LinkedIn	None	None	None
Tools registered	69	15	18
Sales Navigator tools	No	No	No
Recruiter tools	No	No	No
Runs	Either	Hosted by the vendor	Self-hosted
Last code change	15 September 2026 — active	6 August 2026 — active	31 August 2026 — active
Licence	MIT, open source	MIT, open client, closed service	MIT, open source

Anysite MCP Server
Vendor API key
A hosted, paid server that returns structured LinkedIn data — profiles, people search, companies, posts, jobs, the Ad Library — plus a dozen other sources, with server-side filtering and export. No LinkedIn login goes anywhere near it, and it cannot write to LinkedIn at all.
Low riskActive
stdio and Streamable HTTP15 toolsRead 20 September 2026
Insaight
Vendor API key
Research and record-keeping for manual outreach: it briefs you on a person or a company, mines a post's comment thread, and keeps a local ledger of what you sent and what replied. It has no send path at all.
Low riskActive
stdio18 toolsRead 20 September 2026

Provenance

Every page this profile was read from

11 pages — the repository, its documentation and, where one exists, the vendor's own pricing page. Nothing on this profile is summarised from another directory or from a blog post about the project.

All of them read on 20 September 2026. A repository moves faster than a price does: if a tool list or a command here no longer matches the project, the project changed and this page has not been re-read yet.

Where to next

Check what it cannot reach before you build on it

Compare all 13 serversGrouped by what each one hands LinkedIn, not by star count.The limits LinkedIn enforcesWhat any account can do in a week, automated or not.