LinkedInSAFE
A powerful Model Context Protocol server for LinkedIn API integration
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A powerful Model Context Protocol server for LinkedIn API integration
📋 Overview
LinkedIn MCP Server brings the power of the LinkedIn API to your AI assistants through the Model Context Protocol (MCP). This TypeScript server empowers AI agents to interact with LinkedIn data, search profiles, find jobs, and even send messages.
MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs - think of it as a USB-C port for AI applications, connecting models to external data sources and tools.
✨ Features
🔍 LinkedIn API Tools
- Profile Search - Find LinkedIn profiles with advanced filters
- Profile Retrieval - Get detailed information about LinkedIn profiles
- Job Search - Discover job opportunities with customized criteria
- Messaging - Send messages to LinkedIn connections
- Network Stats - Access connection statistics and analytics
🛠️ Technical Highlights
- TypeScript - Built with modern TypeScript for type safety and developer experience
- Dependency Injection - Uses TSyringe for clean, testable architecture
- Structured Logging - Comprehensive logging with Pino for better observability
- MCP Integration - Implements the Model Context Protocol for seamless AI assistant connectivity
- REST Client - Axios-powered API client with automatic token management
🚀 Development
Prerequisites
- Node.js 20+
- npm/yarn
Setup
# Install dependencies npm install # Run the development server npm run start:dev # Build the server npm run build
📦 Installation
To use with Claude Desktop or other MCP-compatible AI assistants:
Configuration
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:
%APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"linkedin-mcp-server": {
"command": "/path/to/linkedin-mcp-server/build/index.js"
}
}
}d78d4f1d4e00OBSERVED · 2026-10-07Connect
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.
claude mcp add linkedin-mcp-server -- npx -y [email protected]
{
"mcpServers": {
"linkedin-mcp-server": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (7)
6 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get-connections | read | Retrieve the current user connections |
get-my-profile | read | Retrieve the current user |
get-network-stats | read | Retrieve network statistics for the current user |
get-profile | read | Retrieve detailed LinkedIn profile information |
search-jobs | read | Search for LinkedIn job postings based on various criteria |
search-people | read | Search for LinkedIn profiles based on various criteria |
send-message | write | Send a message to a LinkedIn connection |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
axios, eventsource-client, lodash, pino, reflect-metadata, tsyringe, zod, @types/lodash
Gates applied: no_behavioural_pass.
d78d4f1d4e00full audit observations/trust-audit/mcp-server/felipfr__linkedin-4.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 |
|---|---|---|---|---|---|
| 2026-10-07 | d78d4f1d4e00 | SAFE | B | 89 | first audit |
Questions
What is the LinkedIn MCP server?
A powerful Model Context Protocol server for LinkedIn API integration
What tools does LinkedIn 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 safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does LinkedIn need?
No credential environment variables were found in its source, so it appears to need none.
How does LinkedIn run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as linkedin-mcp-server at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (d78d4f1d4e00), read on 2026-10-07. The repository is watched and re-audited when it changes.