linkedin-mcp-server

Provides an MCP server that uses browser automation to search LinkedIn for people, companies, and jobs, scrape profile/feed data, and return structured JSON via MCP tools (stdio or streamable-http).

Evaluated Mar 30, 2026 (0d ago)
Repo ↗ API Gateway mcp linkedin browser-automation scraping python fastmcp streamable-http structured-data
⚙ Agent Friendliness
48
/ 100
Can an agent use this?
🔒 Security
41
/ 100
Is it safe for agents?
⚡ Reliability
26
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
60
Documentation
70
Error Messages
0
Auth Simplicity
45
Rate Limits
10

🔒 Security

TLS Enforcement
60
Auth Strength
35
Scope Granularity
20
Dep. Hygiene
55
Secret Handling
40

Uses interactive browser login and persists session data locally (path configurable). No explicit guidance on encrypting session data, least-privilege tool permissions, TLS requirements for HTTP transport, or safe exposure of the streamable-http server. Scraping introduces additional risk surface (untrusted page content processing) and operational risk (credential/session handling).

⚡ Reliability

Uptime/SLA
0
Version Stability
30
Breaking Changes
40
Error Recovery
35
AF Security Reliability

Best When

You need a tool-based MCP integration for structured LinkedIn scraping, and you can run/maintain a headful browser session with persistent local state.

Avoid When

You cannot manage automation risk, session storage security, or you require strict operational guarantees for uptime and error recovery.

Use Cases

  • LLM-assisted research workflows on LinkedIn profiles, companies, and job listings
  • Building agents that can request specific profile/company/job sections as structured JSON
  • Offline enrichment pipelines (within allowed terms/policies) using scraped HTML converted to JSON
  • Remote MCP clients integration via HTTP transport

Not For

  • Production use where compliance with LinkedIn Terms and anti-scraping policies is not ensured
  • High-volume scraping without rate-limit/backoff controls and monitoring
  • Use cases requiring official, guaranteed LinkedIn API data access
  • Security-sensitive environments where storing browser session data on disk is unacceptable

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Interactive LinkedIn login via browser automation (triggered with --login) Session persistence stored locally for subsequent calls
OAuth: No Scopes: No

No OAuth/API-key style auth is described; authentication is done through a persisted browser session and local credential storage. No scope model for tool permissions is described.

Pricing

Free tier: No
Requires CC: No

Repository appears open-source (MIT); costs are operational (hosting, browser automation runtime).

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • LinkedIn pages and DOM structure can change, causing parser/scrape failures
  • Automation may be affected by bot detection/consent flows and network issues
  • HTTP transport requires exposing a server; ensure it is not publicly reachable without controls
  • Browser session persistence stored on disk may need secure filesystem permissions

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for linkedin-mcp-server.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

6461
Packages Evaluated
19942
Need Evaluation
586
Need Re-evaluation
Community Powered