MCP: Meta Content / Social-Listening Intel

An MCP server that exposes meta-content-intel as AI-agent tools - public-post social listening across Facebook + Instagram, the commercial alternative to Meta's academic-only Meta Content Library.

This wrapper lets an AI agent (Claude Desktop, Cursor, OpenAI Assistants, LangChain, any MCP host) call social-listening tools directly. It is x402 (USDC on Base) and Skyfire ready for token-less agentic payments.

Scope. This is organic public-post social listening - not ads (ad-library-intel) and not creator/influencer analytics. See the upstream actor for full details.

Tools

Tool	Does
search_public_posts	Listen to public posts on a topic/keyword across Facebook + Instagram (text, engagement, author, sentiment/theme tags).
get_page_posts	Recent public posts for a Facebook Page / public Instagram profile.
get_hashtag_posts	Public posts for a hashtag across both platforms.
analyze_topic	Aggregate a topic: volume over time, sentiment split, top posts/pages, share-of-voice.
track_topic_mentions	Current public mentions newest-first - the snapshot to diff for new chatter.

Modes

• list_tools - emit the MCP tool catalog + agentic-payment descriptor (free).
• call_tool - invoke one tool (tool + args).
• batch - invoke up to 10 {tool, args} calls in one run.

Example

{ "mode": "call_tool", "tool": "search_public_posts",
  "args": { "keyword": "sustainability", "platforms": ["facebook", "instagram"], "country": "US" } }

Connect it to an MCP client

This Actor is exposed as a remote MCP tool through Apify's hosted MCP server. Point any MCP-compatible client (Claude Desktop, Cursor, VS Code, or an OpenAI / LangChain / LlamaIndex agent) at Apify's server with this Actor enabled:

{
  "mcpServers": {
    "apify": {
      "url": "https://mcp.apify.com?tools=seibs.co/mcp-meta-content-intel",
      "headers": { "Authorization": "Bearer <YOUR_APIFY_TOKEN>" }
    }
  }
}

Get a token (free) from Apify Console -> Settings -> API & Integrations. The Actor then appears as a callable tool. Run mode=list_tools first (free) to fetch every tool's live JSON schema, then call one:

{ "mode": "call_tool", "tool": "search_public_posts", "args": { } }

Prefer a direct call? Hit the Actor straight through the Apify API / SDK - no MCP client required:

from apify_client import ApifyClient
client = ApifyClient("<YOUR_APIFY_TOKEN>")
run = client.actor("seibs.co/mcp-meta-content-intel").call(run_input={
    "mode": "call_tool", "tool": "search_public_posts", "args": {},
})
items = client.dataset(run["defaultDatasetId"]).list_items().items

Pricing

Flat $0.005 per MCP tool call. The upstream meta-content-intel actor charges its own PPE events (post_record $0.004, listening_analysis $0.008, topic_rollup $0.010) to the same run as pass-through. list_tools is free. x402 / Skyfire enable token-less per-call payment when MCP monetization is on.

Legal-safety

Logged-out public posts/pages only; PII minimized (personal-individual authors redacted, Pages/business/verified retained); polite rate limits; fail-soft when blocked. Meta v. Bright Data (2024) supports logged-out scraping of public Meta data. See the upstream actor for the full posture.