Social Media Analytics

Track social media performance and analytics across all platforms. Use when the user says 'show my analytics', 'check social media performance', 'how are my...

Security Scan

The skill's requirements and runtime instructions are internally consistent with a social-media analytics connector that uses an external 'MCP' connector URL (with embedded token) to fetch read-only metrics, but you should verify the connector's actual token scope and the third-party service before trusting it with sensitive accounts.

Purpose & Capability

Name/description (social media analytics) matches the declared requirement: a single MCP Connector link that contains an auth token used to query platform APIs for metrics. No unrelated binaries, env vars, or excessive permissions are requested.

Instruction Scope

SKILL.md instructs the agent to call named boring_* functions (boring_get_performance, etc.) to fetch metrics and to add the MCP link as a connector. The instructions keep scope to reading analytics data, but they explicitly send queries via Boring's servers (an external third party). The file does not instruct reading local files or unrelated credentials.

Install Mechanism

Instruction-only skill with no install spec and no code files — lowest disk/write risk. No downloads or package installs are specified.

Credentials

No environment variables or local keys are required; instead the skill relies on an MCP Connector URL containing an embedded token. That is proportional for this purpose, but an embedded-token URL is a high-value secret: the skill's behavior depends entirely on the token's real permissions (the SKILL.md claims 'read-only', which you cannot verify from the package).

Persistence & Privilege

Skill is not marked always:true, does not request persistent system-wide changes, and is user-invocable. It does not modify other skills or global agent settings per the provided files.

Assessment

This skill appears to do what it claims (read analytics via a Boring 'MCP' connector), but exercise caution before adding the MCP link: treat the MCP URL as a password and do not paste it in public places. Verify on boring.aiagent-me.com that the token is indeed read-only and scoped only to the accounts/metrics you intend to expose. Prefer creating a least-privilege/read-only connector or a limited test account for initial use. Confirm the service's privacy and security posture (who hosts the service, how tokens are stored, rotation/revocation options) and be prepared to revoke the connector if you see unexpected activity. Finally, verify the skill's homepage/source authenticity (owner ID is unknown) before granting access to sensitive or production social accounts.

Boring Social Analytics

Track performance and engagement across all your social media platforms. Powered by Boring.

Security & Data Handling

• MCP link is a credential: Your MCP Server URL (https://boring.aiagent-me.com/mcp/t/xxxxx...) contains an embedded authentication token. Treat it like a password — do not share it publicly.
• Token scope: The embedded token is read-only for analytics. It can only fetch performance metrics and account metadata. It cannot publish, delete, or modify any content on your social media accounts.
• Token storage: The token is stored server-side in Boring's database (MongoDB on DigitalOcean). It is never written to your local filesystem. You can regenerate or revoke it anytime at boring.aiagent-me.com/settings.
• Data flow: Analytics queries are sent from Boring's server (Google Cloud, us-central1) to the platform's API on your behalf. Only performance metrics are retrieved — no content is uploaded or modified.
• No local credentials: No local API keys, environment variables, or secrets are needed. All auth is embedded in the MCP link.
• Third-party service: This skill relies on Boring, an open-source social media management tool. Source code: github.com/snoopyrain.

Prerequisites

1. Sign up at boring.aiagent-me.com with Google
2. Connect accounts — supports Facebook, Instagram, Threads, YouTube, TikTok
3. Get your MCP link: Go to Settings → copy your MCP Server URL (contains your auth token — treat it like a password)
4. Add to Claude: Paste the MCP link as a Connector — no install, no API key needed

Available Analytics Tools

Tool	Data Source	Best For
boring_get_performance	Real-time platform API	Account-level overview (reach, engagement, followers)
boring_get_video_analytics	Real-time platform API	Per-post/video metrics (views, likes, comments, shares)
boring_get_posts_performance	Daily snapshots (collected at 2 AM)	Historical post performance over date ranges
boring_get_publish_history	Boring database	Publishing history and status tracking

Workflow

Step 1: List Accounts

Call boring_list_accounts to see all connected platforms. Show a summary to the user.

Step 2: Determine What the User Wants

User Request	Tool to Use
"How is my account doing?"	boring_get_performance
"Show my best posts"	boring_get_video_analytics
"Performance over the last month"	boring_get_posts_performance
"What did I post recently?"	boring_get_publish_history
"Compare platforms"	boring_get_performance for each platform

Step 3: Fetch Data

Account-Level Performance

boring_get_performance(
  account_id="<account_id>",
  platform="instagram",
  period="week"       // "day", "week", or "month"
)

Returns metrics like reach, follower count, engagement rate, profile views.

Per-Post Analytics (Real-Time)

boring_get_video_analytics(
  account_id="<account_id>",
  platform="instagram",
  limit=20             // max 100
)

Returns per-post data: views, likes, comments, shares for up to 100 recent posts.

Historical Post Performance (Snapshots)

boring_get_posts_performance(
  account_id="<account_id>",
  since="2025-12-01",  // YYYY-MM-DD (default: 30 days ago)
  until="2025-12-31",  // YYYY-MM-DD (default: today)
  limit=20             // max 100
)

Returns post-level engagement, metrics, and content from daily collected snapshots.

Publishing History

boring_get_publish_history(
  limit=20,
  platform="facebook"  // optional filter
)

Returns recent publishing activity with status and post IDs.

Step 4: Present Results

Format the data clearly for the user:

For account overview: Show key metrics in a summary table For post analytics: Rank posts by engagement, highlight top performers For cross-platform comparison: Side-by-side metrics across platforms For historical data: Show trends over time

Metrics by Platform

Facebook

• page_media_view: Total video views
• page_post_engagements: Likes, comments, shares
• page_total_actions: Total page actions

Instagram

• reach: Accounts reached
• follower_count: Total followers
• profile_views: Profile visits
• total_interactions: Likes + comments + saves + shares
• Reels: ig_reels_avg_watch_time, ig_reels_video_view_total_time

Threads

• views: Post views
• likes, replies, reposts, quotes
• followers_count: Account followers

YouTube

• views, likes, comments, shares
• estimatedMinutesWatched: Total watch time
• averageViewDuration: Average view duration
• subscribersGained / subscribersLost

TikTok

• Video views, likes, comments, shares
• Account-level performance metrics

Cross-Platform Comparison

When the user asks to compare platforms, fetch boring_get_performance for each connected account and present a unified table:

| Platform   | Reach   | Engagement | Followers |
|-----------|---------|------------|-----------|
| Facebook  | 12,500  | 1,200      | 5,000     |
| Instagram | 8,300   | 2,100      | 3,200     |
| Threads   | 3,100   | 450        | 1,800     |
| YouTube   | 15,000  | 3,500      | 2,100     |

Error Handling

Error	Solution
InvalidApiKey	MCP link may be invalid — regenerate it at boring.aiagent-me.com Settings
InvalidAccountId	Run boring_list_accounts to get valid IDs
TokenExpired	Reconnect account at boring.aiagent-me.com
No data returned	Account may be newly connected — data collection runs daily at 2 AM

Documentation

Full API docs: boring-doc.aiagent-me.com