Facebook Analytics

Track Facebook Page performance and analytics. Use when the user says 'Facebook analytics', 'Facebook page metrics', 'how is my Facebook doing', 'Facebook en...

Security Scan

The skill is internally consistent: it is an instruction-only integration that uses a single MCP connector URL (containing an embedded read-only token) to fetch Facebook analytics via the Boring service; nothing requested or instructed appears disproportionate to that purpose.

Purpose & Capability

The name/description (Facebook Page analytics) aligns with the requirements and instructions: the skill requires an MCP connector link to Boring and calls Boring API helpers (boring_get_performance, boring_get_video_analytics, etc.). There are no unrelated environment variables, binaries, or config paths requested.

Instruction Scope

SKILL.md restricts runtime actions to listing accounts and calling the named Boring API helper calls. It does not instruct reading arbitrary local files, other credentials, or exfiltrating data to unexpected endpoints. The only credential referenced is the MCP link (described as embedded auth token) which is necessary to access the Boring service.

Install Mechanism

There is no install spec and no code files; this is an instruction-only skill. That is the lowest-risk install model and is coherent with the described behavior.

Credentials

The skill requests no environment variables but requires an MCP Connector URL containing an embedded token. This is a reasonable single credential for a third-party aggregator, but treat the connector like a password: the platform and Boring will receive the token. The SKILL.md claims the token is read-only and stored server-side, but that claim cannot be independently verified from the skill bundle alone.

Persistence & Privilege

always is false and there is no indication the skill modifies other skills or system-wide settings. The skill is user-invocable and may be invoked autonomously by the agent (platform default), which is expected for a connector-style integration.

Assessment

This skill appears coherent for fetching Facebook analytics via the Boring service, but you should: (1) treat your MCP link (the URL with embedded token) like a password — only paste it into trusted connectors and revoke/regenerate it if you suspect misuse; (2) confirm with your organization that giving the MCP connector to the agent/platform is acceptable because the platform will have access to read metrics; (3) review the Boring service homepage/source repository to confirm authenticity and privacy practices if you don't already trust it; (4) if you need stronger assurance, ask the skill owner or platform for proof that the embedded token is truly read-only (scope) and for network/logging details showing what data is accessed. If any instruction asked the agent to provide other credentials or read local files, do not install — this skill does not do that.

Track your Facebook Page performance — reach, engagement, video views, and post-level metrics. 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 Facebook — requires admin access to a Facebook Page
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 Tools

Tool	Data Source	Best For
boring_get_performance	Real-time platform API	Page-level overview (reach, engagement, video views)
boring_get_video_analytics	Real-time platform API	Per-post 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 and filter for facebook platform. Show the user their connected Pages.

Step 2: Determine What the User Wants

User Request	Tool to Use
"How is my Facebook doing?"	boring_get_performance
"Show my best Facebook posts"	boring_get_video_analytics
"Facebook performance over the last month"	boring_get_posts_performance
"What did I post on Facebook?"	boring_get_publish_history

Step 3: Fetch Data

Page-Level Performance

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

Per-Post Analytics (Real-Time)

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

Historical Post Performance (Snapshots)

boring_get_posts_performance(
  account_id="<account_id>",
  since="2025-12-01",
  until="2025-12-31",
  limit=20
)

Step 4: Present Results

Format the data clearly:

• Page overview: Show key metrics in a summary table
• Post analytics: Rank posts by engagement, highlight top performers
• Historical: Show trends over time

Facebook Metrics

Metric	Description
page_media_view	Total video views
page_post_engagements	Likes, comments, shares
page_total_actions	Total page actions

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