LinkedIn BrowserBLOCK
LinkedIn MCP Server for local automation
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A FastMCP-based server for LinkedIn automation and data extraction using browser automation. This server provides a set of tools for interacting with LinkedIn programmatically while respecting LinkedIn's terms of service and rate limits.
Features
- Secure Authentication
- Environment-based credential management
- Session persistence with encrypted cookie storage
- Rate limiting protection
- Automatic session recovery
- Profile Operations
- View and extract profile information
- Search for profiles based on keywords
- Browse LinkedIn feed
- Profile visiting capabilities
- Post Interactions
- Like posts
- Comment on posts
- Read post content and engagement metrics
Prerequisites
- Python 3.8+
- Playwright
- FastMCP library
- LinkedIn account
Installation
- Clone the repository:
git clone [repository-url] cd mcp-linkedin-server
- Create and activate a virtual environment:
python -m venv env source env/bin/activate # On Windows: env\Scripts\activate
- Install dependencies:
pip install -r requirements.txt playwright install chromium
- Set up environment variables:
Create a .env file in the root directory with:
[email protected] LINKEDIN_PASSWORD=your_password COOKIE_ENCRYPTION_KEY=your_encryption_key # Optional: will be auto-generated if not provided
Usage
- Start the MCP server:
python linkedin_browser_mcp.py
- Available Tools:
login_linkedin_secure: Securely log in using environment credentialsbrowse_linkedin_feed: Browse and extract posts from feedsearch_linkedin_profiles: Search for profiles matching criteriaview_linkedin_profile: View and extract data from specific profilesinteract_with_linkedin_post: Like, comment, or read posts
Example Usage
from fastmcp import FastMCP
# Initialize client
client = FastMCP.connect("http://localhost:8000")
# Logdbc1f65c96c1OBSERVED · 2026-10-08Exposed tools (7)
6 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
browse_linkedin_feed | read | Browse LinkedIn feed and return recent posts |
get_linkedin_profile | read | Get LinkedIn profile information |
interact_with_linkedin_post | write | Interact with a LinkedIn post (like, comment) |
login_linkedin | read | Open LinkedIn login page in browser for manual login. |
login_linkedin_secure | read | Open LinkedIn login page in browser for manual login using environment credentials as default values. |
search_linkedin_profiles | read | Search for LinkedIn profiles matching a query |
view_linkedin_profile | read | Visit and extract data from a specific LinkedIn profile |
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | FAIL |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (8)
mcp, fastmcp, python-dotenv, cryptography, asyncio, httpx
load_dotenv() # load environment variables from .env
curl -LsSf https://astral.sh/uv/install.sh | sh
Gates applied: no_behavioural_pass, no_license.
dbc1f65c96c1full audit observations/trust-audit/mcp-server/alinaqi__linkedin-browser.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 |
|---|---|---|---|---|---|
| 2026-10-08 | dbc1f65c96c1 | BLOCK | D | 69 | first audit |
Questions
What is the LinkedIn Browser MCP server?
LinkedIn MCP Server for local automation
What tools does LinkedIn Browser expose?
7 in total: 6 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is LinkedIn Browser safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 4 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does LinkedIn Browser need?
It reads COOKIE_ENCRYPTION_KEY and LINKEDIN_PASSWORD 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 Browser run?
It speaks stdio, so it runs as a local process your client starts.
How current is this page?
The grade is for one exact copy of the source (dbc1f65c96c1), read on 2026-10-08. The repository is watched and re-audited when it changes.