LinkedIn Analytics
SkillDatabases & dataLinkedin-analytics helps your AI make sense of your own LinkedIn numbers using your exported post data. Once added, you can ask why your reach dropped, which posts actually worked, or whether a pattern like carousels doing better is real instead of just a hunch.
Available today. Use it from your connected AI after setup.
No other account needed.
Export your LinkedIn post data, then ask your AI a question like 'why did my reach drop' or 'analyze my posts'.
Then ask your AI: use the LinkedIn Analytics skill
What your AI can do with it
- Show which of your posts actually worked
- Explain why your reach dropped
- Check whether a pattern in your results is real
- Test a hypothesis, such as whether carousels perform better for you
- Answer questions about your own LinkedIn numbers
What this skill tells your AI
The instructions your AI receives, as published by publora/skills in skills/linkedin-analytics/SKILL.md and read by ahel’s review.
Track impressions, engagement and follower growth for your LinkedIn posts and profile, and interact with posts through reactions, comments and reshares. Statistics come from the REST API; reactions, comments, reshares and mention lookups are MCP tools.
Prerequisites
Plans: Works on the free Starter plan. Current limits and pricing: publora.com/pricing.
Getting Started
- Create account at publora.com/register (free)
- Connect LinkedIn via OAuth in Publora Dashboard
- Get API key at app.publora.com/dashboard/api
- Connect your agent to the MCP server at
https://mcp.publora.com, authenticating withAuthorization: Bearer sk_YOUR_API_KEY. In Claude Code:
claude mcp add publora --transport http https://mcp.publora.com \
--header "Authorization: Bearer sk_YOUR_API_KEY"
Claude Desktop, Cursor, Codex, OpenClaw and the claude.ai connector each need a different config file or flow: see client setup for the exact path and snippet.
REST API Fallback
If the MCP server is unavailable or returns errors, use the REST API directly:
Base URL: https://api.publora.com/api/v1
Authentication: Use x-publora-key header (NOT Authorization: Bearer):
# Get your connected platforms
curl -X GET "https://api.publora.com/api/v1/platform-connections" \
-H "x-publora-key: sk_your_api_key"
# Get post statistics
curl -X POST "https://api.publora.com/api/v1/linkedin-post-statistics" \
-H "x-publora-key: sk_your_api_key" \
-H "Content-Type: application/json" \
-d '{
"platformId": "linkedin-abc123",
"postedId": "urn:li:share:7123456789012345678",
"queryTypes": "ALL"
}'
# Get account statistics
curl -X POST "https://api.publora.com/api/v1/linkedin-account-statistics" \
-H "x-publora-key: sk_your_api_key" \
-H "Content-Type: application/json" \
-d '{
"platformId": "linkedin-abc123",
"queryTypes": "ALL"
}'
Platform ID Format: linkedin-{id} where {id} is from /platform-connections response.
Example IDs: linkedin-Tz9W5i6ZYG, linkedin-abc123xyz
📖 Full API documentation: docs.publora.com
Analytics Tools (REST only)
LinkedIn analytics are not exposed as MCP tools. The MCP server carries posting, media and LinkedIn engagement tools; statistics live only on the REST API, so call these endpoints directly with the x-publora-key header. Asking an agent for an linkedin_post_stats MCP tool will fail: there is no such tool.
POST /linkedin-post-statistics
Engagement metrics for one post.
Body:
platformId: platform connection ID (e.g.linkedin-abc123), fromlist_connectionspostedId: post URN (urn:li:share:...orurn:li:ugcPost:...)queryTypes(optional):IMPRESSION,MEMBERS_REACHED,RESHARE,REACTION,COMMENT, orALL
Returns: impressions, unique impressions (members reached), reactions, comments, reshares, and a cached flag telling you whether the numbers came from cache.
POST /linkedin-account-statistics
Aggregated statistics for the account.
Body: platformId, optional queryTypes, optional aggregation (DAILY or TOTAL, default TOTAL).
POST /linkedin-followers
Follower count or growth over time.
Body: platformId, optional period (lifetime or daily), optional dateRange ({start: {year, month, day}, end: {year, month, day}}).
POST /linkedin-profile-summary
Combined profile overview: followers plus statistics.
Body: platformId, optional dateRange.
curl -X POST "https://api.publora.com/api/v1/linkedin-post-statistics" \
-H "x-publora-key: sk_your_api_key" \
-H "Content-Type: application/json" \
-d '{"platformId": "linkedin-abc123", "postedId": "urn:li:share:7123456789012345678", "queryTypes": "ALL"}'
Engagement Tools
linkedin_create_reaction
React to a LinkedIn post.
Parameters:
postedId: LinkedIn post URNplatformId: Platform connection IDreactionType: One of the following:
| Type | Description |
|---|---|
LIKE | Standard thumbs up |
PRAISE | Clapping hands / applause |
EMPATHY | Heart / love |
INTEREST | Lightbulb / insightful |
APPRECIATION | Supportive |
ENTERTAINMENT | Funny / laughing |
linkedin_delete_reaction
Remove your reaction from a post.
Parameters:
postedId: LinkedIn post URNplatformId: Platform connection ID
linkedin_create_comment
Post a comment on a LinkedIn post (max 1,250 characters).
Parameters:
postedId: LinkedIn post URNplatformId: Platform connection IDmessage: Comment text (max 1,250 characters)parentComment(optional): Comment URN for nested replies
linkedin_delete_comment
Remove a comment you made.
Parameters:
postedId: LinkedIn post URNcommentId: Comment URN or numeric IDplatformId: Platform connection ID
linkedin_create_reshare
Reshare an existing post, with optional commentary.
Parameters:
platformId: platform connection IDparent: the post to reshare, as a share URN (urn:li:share:...orurn:li:ugcPost:...). Note the name: this tool takesparent, notpostedIdlike the reaction and comment tools.commentary(optional): your text above the reshare, up to 3,000 charactersvisibility(optional):PUBLICorCONNECTIONS, defaultPUBLIC.CONNECTIONSis for personal accounts.
Note: a LinkedIn feed URL carries an activity id, which is not always the same as the share id. Use the postedId returned by get_post, not a hand-converted activity id.
linkedin_list_mentionables
Resolve names to the URNs that @mentions need, so you never hand-write a member id.
Parameters:
q(optional): the name to search forlimit(optional): how many results to return
Both are optional, and this tool takes no platformId: it searches across the account rather than one connection.
Example Prompts
Weekly Performance Review
Analyze my LinkedIn performance for the last 7 days.
Show me:
1. Which posts performed best
2. My engagement rate trends
3. Follower growth
4. Recommendations for improvement
Post Analysis
Get detailed stats for my last 5 LinkedIn posts and identify patterns in what content resonates with my audience.
Engagement Campaign
React with PRAISE to my colleague's post about their promotion (urn:li:share:123456) and add a congratulatory comment.
Follower Tracking
Show my LinkedIn follower growth for the last 30 days. How many new followers did I gain each week?
Metrics Reference
| Metric | Description |
|---|---|
IMPRESSION | Total times content appeared in feeds |
MEMBERS_REACHED | Unique LinkedIn members who saw the post |
RESHARE | Number of reposts/shares |
REACTION | Total reactions (all types combined) |
COMMENT | Number of comments |
Engagement Rate Benchmarks
Average LinkedIn engagement rates by follower count:
| Followers | Good Engagement Rate |
|---|---|
| < 5K | 3-5% |
| 5K-50K | 2-3% |
| 50K+ | 1-2% |
Good performing posts typically have:
- 2x your average impressions
- Comment-to-reaction ratio above 10%
- Engagement rate above your baseline
Important Notes
-
Analytics delay: LinkedIn analytics may take up to 24 hours to fully populate. Querying immediately after posting returns partial data.
-
URN formats: LinkedIn URLs use
urn:li:activity:xxxbut the API requiresurn:li:share:xxxorurn:li:ugcPost:xxx. Use thepostedIdfrom Publora'sget_postresponse for accurate URNs. -
Caching: Analytics responses may be cached. The response includes a
cachedfield indicating if data came from cache. -
Rate limits: LinkedIn has approximately 200+ API calls per hour. Implement backoff on 429 errors.
Troubleshooting
| Error | Cause | Solution |
|---|---|---|
| "Platform ID not found" | Invalid connection ID | Run list_connections to get valid IDs |
| "Post not found" | Wrong URN format | Use urn:li:share: or urn:li:ugcPost: format |
| 429 Too Many Requests | Rate limited | Wait and retry with exponential backoff |
| "message cannot exceed 1250 characters" | Comment too long | Shorten comment to under 1,250 chars |
Signals
- GitHub stars
- 47
- Forks
- 5
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
linkedin-analytics- Source
- github.com/publora/skills