MCP server · personal LinkedIn profiles

Your agent already writes your posts.Give it the data to write your next one.

Connect your LinkedIn post analytics to the AI assistant you already use. See what performed, compare results, and use what’s working to guide your next draft.

Read-only accessOne personal LinkedIn profile

~/posts · claude · 96×30

✓ linkintel connected · 142 posts measured · read-only

You asked: Which of my posts performed best? Tool call: get_top_posts · by impressions LinkIntel answered: Depends what you mean by best. The post about reviewing 200+ DevRel CVs got the most reach: 9,498 impressions at 0.22% engagement. Your satirical job ad reached 7,498 at 0.92%, so 21% fewer people and roughly four times the response. You asked: How does last month compare with the one before? Tool call: compare_periods · 30d vs previous 30d LinkIntel answered: 20,806 impressions, down 73%. Engagement went the other way: 0.78% to 1.27%, up 63%. Fewer people saw your posts and noticeably more of them did something about it. You asked: Anything unusual in there? Tool call: detect_anomalies · impressions LinkIntel answered: The CV review post. Its reach sits well outside your normal range while its 0.22% engagement sits inside it. Reach moving on its own usually points at distribution rather than the writing. You asked: So what should I write next? LinkIntel answered: Both of your strongest posts were takes on hiring. The one that got replies argued a position; the one that got reach only described a thing. If you want the replies, argue something.

Example using the founder’s real data · 12 Aug 2026

One MCP, your harness

  • Claude
  • Claude Code
  • ChatGPT
  • Cursor
  • VS Code
  • Zed
  • Windsurf
  • OpenClaw

What you can ask

Questions, not dashboards.

Every question maps to a real tool your agent calls, mid-draft, without leaving the thread. It reads the numbers and answers in a sentence you can act on.

  • How did my posts do last month?

    get_performance_summary
  • Which post got the most reach?

    get_top_posts
  • Better or worse than last month?

    compare_periods
  • Which days were unusually good?

    detect_anomalies
  • What do my best posts have in common?

    get_content_insights
  • How did that one post actually do?

    get_post_performance
  • What does my reach look like day by day?

    get_daily_trend
  • How fresh is this data, really?

    get_data_status

It will also tell you when the data cannot answer the question, which is more often than most analytics tools admit.

Client results

Use what works to guide what comes next.

In one client engagement, we used LinkIntel to evaluate LinkedIn content performance and guide decisions about what to create next.

One anonymous client

Six-month reporting window

impressions
2M+
comments
2,300+
posts published
60+
Review performanceFind what worksGuide the next draft

Source: client Buffer analytics export; workflow described by the content practitioner. Figures rounded down for privacy. Comments include replies. The engagement ended around the final month. Results reflect the overall content work and do not isolate LinkIntel’s contribution.

Setup

From your posts to your first answer.

No dashboard to learn, no tracking script, and nothing to install on LinkedIn itself.

  1. 01

    Connect your LinkedIn

    One read-only permission, granted on LinkedIn's own consent screen, before you pay anything. We never see your password, and LinkIntel can never publish as you.

  2. 02

    Subscribe

    One plan, billed monthly, only once LinkedIn is connected. Cancel any time and keep access until the month you've paid for ends.

  3. 03

    Bring your post history

    Typefully, Postiz, a webhook from anything else, or LinkedIn's own .xlsx export. LinkedIn will measure a post, but its API cannot list which posts you published.

  4. 04

    Ask, learn, repeat

    Add the command below to your assistant, then ask it about your posts. It stays current on its own, and says so when the data is incomplete.

Add it to Claude Code
$ claude mcp add --transport http linkintel https://www.getlinkintel.com/api/mcp \
  --header "Authorization: Bearer YOUR_KEY"

Claude Desktop, Cursor or another JSON-config client? The equivalent block is in the MCP docs. Want your agent to do the whole thing? Hand it SKILL.md.

One simple plan

Know what’s working on LinkedIn.

Your post performance, ready to explore in the AI assistant you already use.

LinkIntel

$39/month

One personal LinkedIn profile.
All features included.

Compare posts. Spot trends. Inform your next draft.

Get started

Billed monthly. Cancel anytime; access continues until the end of your paid billing period. No free trial.

Everything you need to learn from your posts

  • Find your strongest posts

    Rank your content by impressions and engagement rate.

  • See how your results change

    Compare periods, follow daily trends, and spot unusual days.

  • Ask in the assistant you already use

    Bring your performance into the conversation where you write.

  • Explore your web dashboard

    Your post analytics, ready to browse whenever you need them.

  • Bring your publishing history

    Import from Typefully, Postiz, webhooks, or a LinkedIn export.

Read-only LinkedIn accessOfficial LinkedIn analyticsYour data stays yours

Questions

LinkIntel questions, answered plainly.

See every question
Does LinkIntel access my LinkedIn account?

Yes, in one narrow way. You grant a single read-only permission, r_member_postAnalytics, on LinkedIn's own consent screen. It lets us read performance metrics for posts you published yourself. We never see your password: LinkedIn handles the sign-in and only hands us a token for that one permission.

Can LinkIntel post, comment or react on my behalf?

No. We hold no write permission of any kind, so it is not a matter of policy but of capability: the integration cannot publish, comment, react, message or follow. If you ever see LinkIntel ask for a write permission on LinkedIn's consent screen, something is wrong and you should decline it.

What exactly can it see?

Performance metrics for your own posts: impressions, members reached, reactions, comments, reshares, saves, sends and link clicks. It cannot see your messages, your connections, your feed, your profile viewers, or anybody else's posts.

How do I disconnect it?

Go to LinkedIn's permitted services page and remove LinkIntel. You do not need to ask us or wait for us, and it takes effect immediately. You can also ask us to delete the metrics we have already stored.

What does it cost?

$39 a month, one plan, no trial. You connect the LinkedIn profile you want to measure first, and subscribing activates it. Cancel whenever you like and it keeps working until the end of the month you have paid for.

Why is there no free tier?

Daily syncing uses LinkedIn's limited API allowance. LinkIntel is a paid service with limited sync capacity. If we are full, we will tell you before you pay.

Do I need Claude to use this?

LinkIntel is delivered as an MCP server, so it is designed to be asked questions through an AI assistant that supports MCP, such as Claude. There is also a web view of the same data if you would rather look at it directly.

Who owns my data?

You do. Your metrics are stored against your own account, visible only to you, and are never sold, shared with third parties, or used to train models. You can request deletion at any time.

Is my data secure?

Metrics are stored in our own infrastructure on encrypted, access-controlled cloud hosting, scoped so that one account cannot read another's. We store the minimum needed to answer questions about your posts, and no LinkedIn password ever reaches us.

How current are the numbers?

Your metrics sync automatically, and LinkIntel will tell you how fresh the data is and how many of your posts are measured rather than quietly presenting a partial picture as a complete one. You can also trigger a fresh pull yourself.

I run a LinkedIn company Page, not a personal profile. Can I use this?

No. LinkIntel reads the posts you publish on your own profile. Organization Page analytics is a different LinkedIn API that this product no longer covers.

Your next post is getting drafted anyway. Let it learn from the last hundred.

Connect LinkedIn first, then subscribe. No trial. Cancel any time and keep access until the month you’ve paid for ends.