QAmcp

Copied. Paste it into Claude Code, Cursor or Codex:Fetch and follow the instructions at https://qamcp.dev/setup.md to test my MCP server.

Your AI finds your server in your project, tests it with QAmcp, explains what's wrong in plain words, fixes it with your OK, and tests again. Read the instructions

SoonYour score can change any day. QAmcp Monitor tests your server every hour and emails you when it breaks.See what Monitor does →

Directory / Flux LinkedIn MCP

Flux LinkedIn MCP

Q: Is Flux LinkedIn MCP server safe?

QAmcp's test on 2 Nov 2026: None of the hidden-instruction wordings we know were found in its tool descriptions. 0 of its 60 tools are labeled read-only; the others may change or send things. Overall it scored 77/100 on 2 Nov 2026. A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.

by fluxgraph.app · https://www.fluxgraph.app/mcp

LinkedIn intelligence: post analytics and research for public profiles and company pages.

66 tools✓ no account neededPricing: on their site

See pricing →Visit website

77 /100

PASS · WITH NOTES

Partial: 8 of 11 checks · 2 Nov 2026

Is Flux LinkedIn MCP server safe?

None of the hidden-instruction wordings we know were found in its tool descriptions.
0 of its 60 tools are labeled read-only; the others may change or send things.
Overall it scored 77/100 on 2 Nov 2026.

A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.

What it can do

60 tools, in the server's own words.

list_profiles

List all tracked LinkedIn profiles for the authenticated user.

preview_profile

Analyze a public LinkedIn profile or company page without a Flux account: pulls the latest ~50 posts (once per profile) and returns a preview id, post count an…

preview_posting_insights

Best day, hour, format and length for a previewed profile (from preview_profile).

claim_preview

Make a profile from preview_profile your own Flux dashboard.

get_posts

List a tracked profile's persisted posts with full metrics and text — query against the local post library, no LinkedIn pull, free.

get_profile_summary

Get KPI summary for a tracked profile: total posts, average engagement (broken down by likes/comments/shares/conversation rate), posts per week, engagement tre…

get_posting_insights

Get optimal posting patterns for a profile: best day of week, best hour, format performance breakdown, and character length sweet spot.

get_topic_insights

Surface the most-frequent topics in a profile's posts, with engagement context.

get_engagement_trends

Get engagement time series for a profile with gap-filled buckets, rolling averages, and trend direction.

search_posts

Keyword + semantic search over persisted posts in the local library — full-text + pgvector cosine, no LinkedIn pull, free.

get_credit_balance

Return the authenticated user's current credit balance, this period's monthly allocation, and credits used since the period started.

get_usage_history

Return recent credit_ledger transactions for the authenticated user.

get_cost_estimate

Given an MCP tool name, return its credit cost so you can preview an action before running it.

create_stream

Create a new research stream (external profile, company, topic, person interests, hiring signals, or ad watch).

list_streams

List all research streams for the authenticated user (external profiles, companies, topics, person interests, hiring signals, ad watches, and own_profile).

get_stream_feed

Return the most recent posts a stream has collected into the library, newest first by published_at.

pause_stream

Pause a stream so it stops running on its cron schedule.

resume_stream

Resume a paused stream.

delete_stream

Delete a stream and its stream_runs.

run_stream_now

Trigger an immediate run of an active stream, bypassing its schedule.

linkedin_profile_info

Fetch a LinkedIn person profile (headline, current role, work history, education, location).

linkedin_profile_posts

Fetch recent posts from a LinkedIn person profile.

linkedin_company_posts

Fetch recent posts from a LinkedIn company page.

linkedin_post_search

Search LinkedIn posts by keyword.

and 36 more

Test results

Safe mode: only tools labeled read-only were run. How the test works

!
Ready for the newest MCP version
1 warning
- !Uses an older MCP version (2025-11-25). It works today, but it isn't on the July 2026 version (2026-07-28) yet.
note
!
Every tool is described
6 warnings
- !linkedin_profile_posts and linkedin_company_posts have nearly the same description (77% of their words are shared; the only difference: "person", "brief", "render" vs "company"), so an AI may not know which to pick
- !linkedin_profile_reactions and linkedin_profile_comments have nearly the same description (75% of their words are shared; the only difference: "reacted" vs "commented", "conversation", "partner"), so an AI may not know which to pick
- !add_to_segment and remove_from_segment have nearly the same description (71% of their words are shared; the only difference: "add", "existing" vs "remove", "missing"), so an AI may not know which to pick
- !resolve_segment and resolve_collection have nearly the same description (70% of their words are shared; the only difference: "segment", "audience", "person" vs "collection", "post", "user"), so an AI may not know which to pick
- !linkedin_post_search and linkedin_company_search have nearly the same description (67% of their words are shared; the only difference: "post" vs "companie", "filter", "industryid"), so an AI may not know which to pick
- !linkedin_people_search and linkedin_company_search have nearly the same description (60% of their words are shared; the only difference: "people", "company", "title" vs "companie", "industryid"), so an AI may not know which to pick
note
!
Tools are labeled safe or dangerous
4 warnings
- !66 of 66 tools have no safety label (read-only or dangerous): list_profiles, preview_profile, preview_posting_insights, claim_preview, get_posts, get_profile_summary, get_posting_insights, get_topic_insights, get_engagement_trends, search_p
- !delete_stream: Name sounds like it deletes something, but it is not labeled dangerous
- !remove_from_segment: Name sounds like it deletes something, but it is not labeled dangerous
- !remove_from_collection: Name sounds like it deletes something, but it is not labeled dangerous
note
!
Follows MCP best practices (not scored yet)
3 tips (not scored)
- !66 tools not labeled read-only don't say whether running them twice is safe (idempotentHint): list_profiles, preview_profile, preview_posting_insights, claim_preview, get_posts, get_profile_summary and 60 more
- !66 tools don't say whether they reach outside services like the web (openWorldHint): list_profiles, preview_profile, preview_posting_insights, claim_preview, get_posts, get_profile_summary and 60 more
- !The tool list is about 62 KB (roughly 16k tokens). AI apps send it with every message, so it takes that much of the AI's memory before any work starts.
note
✓
ConnectsConnected in 734 ms
pass
✓
Lists its toolsFound 66 tools
pass
✓
No known hidden instructionsNone of the hidden-instruction wordings we know were found in tool descriptions. New wordings can get past this check.
pass
✓
Fast enough
All good
- ✓Connecting took 734 ms
- ✓Listing tools took 123 ms
pass
–
Tools work with good inputs
Not tested
- –list_profiles: Not run: no safety label (if you own this server, test again in owner mode)
- –preview_profile: Not run: no safety label (if you own this server, test again in owner mode)
- –preview_posting_insights: Not run: no safety label (if you own this server, test again in owner mode)
- –claim_preview: Not run: no safety label (if you own this server, test again in owner mode)
- –get_posts: Not run: no safety label (if you own this server, test again in owner mode)
- –get_profile_summary: Not run: no safety label (if you own this server, test again in owner mode)
- –get_posting_insights: Not run: no safety label (if you own this server, test again in owner mode)
- –get_topic_insights: Not run: no safety label (if you own this server, test again in owner mode)
- and 32 more
not tested
–
Bad inputs give a clean errorNot tested
not tested
–
Tools work togetherNo safe tool returned data to start a chain from, so chains were not tested (not counted either way)
not tested
–
No secrets leakedNo error messages to check
not tested

Test it yourself

Free and open source. Same checks, same score.

npx qamcp-cli https://www.fluxgraph.app/mcp

Show this score on GitHub

Free for every server in the directory. Paste this into your README: the badge shows the score from our latest test.

[![QAmcp score](https://qamcp.dev/s/app-fluxgraph-linkedin.svg)](https://qamcp.dev/s/app-fluxgraph-linkedin.html)

Score over time

2 Nov 202677

One test so far. New tests will show here.

Reviews

Coming soon: reviews from people who use Flux LinkedIn MCP, signed in with GitHub, one per person. Reviews never change the score.

Is this your server? Get an alert the moment it breaks.

QAmcp Monitor (coming soon) tests it every hour and emails you when it goes down, the score drops, a tool changes or a secret leaks. You'll also be able to claim this page and get a verified owner mark. Founding price: $19/month for life for the first 50 teams.

Have a concern, or want it removed? Ask us and we'll take it off the list. How the directory works