- Home
- Skills
- Social Media
- LinkedIn MCP Posting Audit
Works with the AI Agents you already use
LinkedIn MCP Posting Audit
Use the free Flux LinkedIn MCP preview to find out what actually works on a LinkedIn account, measured against its own baseline.
Free
LinkedIn MCP Posting Audit
Example session with this skill installed
When should I post on LinkedIn, and what's actually working? https://www.linkedin.com/in/trevormfox. I'm on Pacific time.
- Read your context and instructions
- Compiled the linkedin mcp posting
Bottom line: Posts on Tuesday did the best of any day, averaging 1.8× the baseline across 12 posts.
Sample: 50 original posts averaging 11.7 engagements each, from the Flux LinkedIn MCP.
| Bucket | Posts | Avg engagement | vs baseline | Confidence |
|---|---|---|---|---|
| Tuesday | 12 | 20.9 | 1.8× | Pattern |
| 14:00 UTC | 7 | 26.1 | 2.2× | Directional, worth testing |
| Article | 3 | 29.3 | 2.5× | Anecdote, no recommendation |
What drags: Friday (10 posts, 0.5×) and posts under 200 characters (12 posts, 0.6×).
Conversation: Posts of 200–400 characters drew fewer likes than 600–800 (9.6 vs 11.3) but more comments (5.4 vs 3.0), so the shorter band may be better for someone seeking leads.
Run this next: Publish your next 6 text or image posts on Tuesdays, and compare them with your text and image average of 8.1. An average of 10.6 or higher supports keeping the slot.
Connects securely to your tools. The creator never sees your data.
About this skill
What it does
This skill gives your agent a LinkedIn MCP workflow for one question: what actually works on this account? Give it a public LinkedIn profile or company URL. It pulls the last ~50 original posts through the Flux LinkedIn MCP and shows which days, hours, formats and lengths beat that account's own baseline.
How it is different
Most analytics name a "best" time or format even when only a few posts sit behind it. This skill grades every finding by sample size, so a format that won on 3 posts gets labeled an anecdote and is not recommended. Every report ends with one specific test to run, including the result that would confirm it.
How it works
- Flux LinkedIn MCP: your agent uses the
preview_profileandpreview_posting_insightstools if they are connected, or calls the public endpoint athttps://www.fluxgraph.app/mcp. Neither needs an account or an API key. - Pasted posts: if you would rather not make a network call, paste your post data and the agent does the math locally.
Where it stops
The audit measures engagement, not reach, because the data has no impressions. It covers about the last 50 original posts and shows correlation, not cause. Flux offers full post history and weekly refreshes for anyone who needs more.
It measures engagement, not reach, because the data has no impressions. It covers about the last 50 original posts, excluding reposts and quote posts. Day and hour are measured separately and in UTC, and findings are correlations. Anonymous use is limited to 10 calls per hour per network.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 13 days ago
- Free with an Agensi account
Requires
Permissions
Allowed Hosts
Only the LinkedIn URL you provide is sent to Flux. The pasted-posts route makes no network calls.