LinkedIn ScraperCAUTION
Open-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI agent access to profiles, companies, jobs, and messages.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
MCP Server for LinkedIn An MCP server that connects AI assistants like Claude to LinkedIn through your own logged-in browser session. Look up profiles and companies, send messages, manage your inbox, or search for jobs. All browser actions run locally on your machine.> This is an independent open-source project, not affiliated with, authorized by, endorsed by, or sponsored by LinkedIn or Microsoft. LinkedIn is a trademark of LinkedIn Corporation and is used here only to identify the service this software interacts with.LinkedIn MCP Sponsor > This MCP server is supported by **Unipile**
69ab3685578eOBSERVED · 2026-09-18Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-server-linkedin --env PROXY_SERVER=${PROXY_SERVER} --env PROXY_USERNAME=${PROXY_USERNAME} --env PROXY_PASSWORD=${PROXY_PASSWORD} --env PROXY_SERVER=${PROXY_SERVER} -- None mcp-server-linkedin==4.24.3claude mcp add linkedin-mcp-server:4.24.3 --env PROXY_SERVER=${PROXY_SERVER} --env PROXY_USERNAME=${PROXY_USERNAME} --env PROXY_PASSWORD=${PROXY_PASSWORD} --env PROXY_SERVER=${PROXY_SERVER} -- docker run -i --rm docker.io/stickerdaniel/linkedin-mcp-server:4.24.3:NoneExposed tools (10)
9 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
close_session | read | Close the current browser session and clean up resources. |
connect_with_person | read | |
get_company_employees | read | |
get_company_posts | read | |
get_company_profile | read | |
get_job_details | read | |
get_sidebar_profiles | read | |
search_companies | read | |
search_people | read | |
send_message | write |
Trust audit
CAUTIONgrade C · trust 70/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (5 observation(s))
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- found
Findings (25)
curl -s -D /tmp/repro-$NUM-headers -X POST http://127.0.0.1:$PORT/mcp \
curl -s -X POST http://127.0.0.1:$PORT/mcp \
curl -s -X POST http://127.0.0.1:$PORT/mcp \
curl -s -D /tmp/verify-pr-$PR-headers -X POST http://127.0.0.1:$PORT/mcp \
curl -s -X POST http://127.0.0.1:$PORT/mcp \
token = "private-access-token"
secret = "proxy-password-must-not-cross"
.coveragerc
.mcpbignore
.pre-commit-config.yaml
CLAUDE.md
await scraper.scrape_company("../../feed", {"about"})await scraper.get_company_employees("../../feed")await reader._open_conversation_by_username("../../feed")await reader.get_conversation(thread_id="../../feed")
linkedin_username="../../feed", thread_id="2-direct", index=-1
[![uvx](https://img.shields.io/badge/uvx-Quick_Install-de5fe9?style=for-the-badge&logo=data:image/svg+xml;base64,PHN2ZyB3aWR0aD0iNDEiIGhlaWdodD0iNDEiIHZpZXdCb3g9IjAgMCA0MSA0MSIgZmlsbD0ibm9uZSIgeG1sbnM
[![Codex Plugin](https://img.shields.io/badge/Codex-Plugin-24292f?style=for-the-badge&logo=data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9IjAgMCAyNCAyNCI%2BP
encrypted_key = base64.b64decode(payload["os_crypt"]["encrypted_key"])
decoded = bytes.fromhex(nonce)
decoded = bytes.fromhex(value)
"",
"",
"",
"",
Gates applied: no_behavioural_pass.
69ab3685578efull audit observations/trust-audit/mcp-server/stickerdaniel__linkedin-scraper.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-09-18 | 69ab3685578e | CAUTION | C | 70 | first audit |
Questions
What is the LinkedIn Scraper MCP server?
Open-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI agent access to profiles, companies, jobs, and messages.
What tools does LinkedIn Scraper expose?
10 in total: 9 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is LinkedIn Scraper safe to connect to an agent?
With care. The audit graded it C (70/100) and found 25 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does LinkedIn Scraper need?
It reads PROXY_PASSWORD, PROXY_SERVER and PROXY_USERNAME from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does LinkedIn Scraper run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as mcp-server-linkedin.
How current is this page?
The grade is for one exact copy of the source (69ab3685578e), read on 2026-09-18. The repository is watched and re-audited when it changes.