Server data from the Official MCP Registry
LinkedIn for AI assistants — search, profiles, jobs, feed, messaging, and gated writes.
LinkedIn for AI assistants — search, profiles, jobs, feed, messaging, and gated writes.
This LinkedIn MCP server implements browser automation to access LinkedIn's Voyager API with structured safety controls (daily caps, pacing, circuit breaker). The codebase is well-intentioned and properly documented, but contains moderate-severity concerns: (1) reliance on fragile, undocumented GraphQL queryId values that rotate frequently and have no live-capture fallback mechanism in production, (2) write operations ship with best-known but unverified payloads that may fail silently or trigger account restrictions, (3) broad browser-based permissions (network, file I/O, subprocess via patchright) that enable LinkedIn account automation in violation of ToS, and (4) incomplete input validation on user-supplied search keywords and profile IDs. The server is not malicious, but users should understand the account-safety risks and technical fragility inherent in automating a platform that actively blocks such access. Supply chain analysis found 4 known vulnerabilities in dependencies (1 critical, 3 high severity). Package verification found 1 issue.
4 files analyzed · 13 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-devag7-linkedin-mcp": {
"args": [
"-y",
"linkedin-mcp-tools"
],
"command": "npx"
}
}
}Be the first to review this server!
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.
by Microsoft · Content & Media
Convert files (PDF, Word, Excel, images, audio) to Markdown for LLM consumption