Flux LinkedIn MCP
app.fluxgraph/linkedin · v1.0.1 · score 89/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
LinkedIn intelligence: post analytics and research for public profiles and company pages.
Source: https://github.com/elegant-atomics/linkedin-mcp
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 72 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 3 tool(s) can execute commands or delete data (delete_stream, remove_from_segment, remove_from_collection). Require confirmation before the agent calls them. |
What was checked
- https://www.fluxgraph.app/mcp: answers without auth
Public tools: list_profiles, preview_profile, preview_posting_insights, preview_search_posts, claim_preview, get_posts, get_profile_summary, get_posting_insights, get_topic_insights, get_engagement_trends, search_posts, get_credit_balance, get_usage_history, get_cost_estimate, create_stream, list_streams, get_stream_feed, pause_stream, resume_stream, delete_stream, run_stream_now, linkedin_profile_info, linkedin_profile_posts, linkedin_company_posts, linkedin_post_search, linkedin_profile_reactions, linkedin_profile_comments, linkedin_job_search, linkedin_ad_search, linkedin_people_search
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/app-fluxgraph-linkedin-57bee2f3)