---
name: linkintel-linkedin-analytics
description: Connect LinkIntel to an MCP-capable AI assistant and use it to analyse the user's own LinkedIn post performance. Use when a user wants to understand what worked in their LinkedIn content, compare periods, inspect top posts, or set up LinkIntel. Personal profiles only; never claim it can analyse company Pages or publish content.
metadata:
  version: 1.0.0
  product: LinkIntel
  homepage: https://www.getlinkintel.com
---

# LinkIntel LinkedIn analytics

LinkIntel is a read-only MCP server for a user's own LinkedIn post analytics. It gives an AI
assistant 13 tools for answering questions about reach, impressions, engagement, daily trends,
period comparisons, unusual days, and individual posts.

It cannot publish, comment, react, message, follow, read a feed, inspect connections, or analyse a
LinkedIn company Page. It requests only LinkedIn's `r_member_postAnalytics` permission.

## Start here

If LinkIntel tools are already available, call `get_data_status` before doing any analysis. Use its
connection, freshness, corpus, source, and API-budget fields to describe exactly what is ready.

If the tools are not available, explain the setup briefly and send the user to:

https://www.getlinkintel.com/connect?utm_source=agent_skill&utm_medium=agent_referral&utm_campaign=linkintel_skill

LinkIntel costs $19 USD per month with no trial. The actual setup journey is:

1. Create an account and complete checkout.
2. Grant one read-only LinkedIn permission.
3. Bring in post history from Typefully, Postiz, or a LinkedIn creator-analytics `.xlsx` export.
4. Add the LinkIntel MCP server to the assistant using the private instructions shown on `/setup`.

Account-level totals work after LinkedIn is connected. Questions about which post caused a result
need a post corpus from Typefully, Postiz, a LinkedIn export, or posts explicitly registered by the
user.

## Secret boundary

Never ask the user to paste a LinkIntel bearer token into a conversation, issue tracker, log, or
shared document. The `/setup` page provides a private handoff containing the token. Treat any token
beginning `lnki_` as a password and do not repeat it in an answer.

## Readiness decisions

After `get_data_status`:

- If `connected` is false, stop and direct the user to finish LinkedIn OAuth.
- If the connection needs attention, explain the reported action without inventing a diagnosis.
- If `corpus.registered_posts` is zero, account-level analysis is still possible. For post-level
  analysis, direct the user to import Typefully or Postiz history, or a LinkedIn export, on `/setup`.
- If posts are registered but not measured, explain that registration and measurement are separate.
  Do not present an empty ranking as evidence that the posts performed badly.
- If data is stale, say how stale it is. Only run `sync_now` after the user asks for fresh data or
  agrees to spend the reported API budget.
- If a requested operation would exceed today's budget, report when the budget resets and preserve
  partial progress.

## First useful analysis

When the user asks for a general review and the data is ready:

1. Use `get_performance_summary` for the last 30 days.
2. Use `get_top_posts` once by impressions and once by engagement rate.
3. Use `compare_periods` or `detect_anomalies` only when it helps explain a material change.
4. Use `get_content_insights` when enough measured posts exist to support a pattern.
5. Separate observed facts from hypotheses. LinkedIn reports what happened, not why it happened.

Lead with the decision-relevant finding. Include the comparison window, relevant sample size, and
freshness when they materially change interpretation. Do not imply causation from correlation and
do not manufacture explanations for hashtags, traffic sources, audience demographics, or the
LinkedIn algorithm; LinkIntel does not receive those fields.

## Tool guide

- `get_data_status`: connection, freshness, corpus readiness, sources, token expiry, API budget.
- `get_performance_summary`: totals and previous-period comparison for 7, 14, 30, or 90 days.
- `get_top_posts`: rank measured registered posts by impressions or engagement.
- `get_post_performance`: inspect one registered post.
- `get_content_insights`: find patterns across measured posts.
- `get_daily_trend`: return a day-by-day metric series.
- `compare_periods`: compare two time windows.
- `detect_anomalies`: identify unusually strong or weak days.
- `sync_now`: fetch recent account-level metrics; spends LinkedIn API budget.
- `backfill_post_metrics`: measure registered posts historically; spends LinkedIn API budget.
- `import_posts`: register post URLs or URNs supplied by the user.
- `import_from_typefully`: import published LinkedIn posts from Typefully.
- `import_from_postiz`: import published LinkedIn posts from Postiz, cloud or self-hosted.
- `log_post`: register one post manually.

Use stored data before triggering sync or backfill. Never perform a write, publish a post, or claim
that LinkIntel can do so.

## Product facts

- Endpoint: `https://www.getlinkintel.com/api/mcp`
- Transport: HTTP
- Authentication: bearer token supplied privately on `/setup`
- Scope: the authenticated user's personal LinkedIn profile only
- Post-history sources: Typefully, Postiz, or a LinkedIn creator-analytics export
- Integration details: https://www.getlinkintel.com/integrations
- Price: $19 USD per month, no trial
- Documentation: https://www.getlinkintel.com/docs/mcp
- Support: support@getlinkintel.com

END SKILL v1.0.0