Unified social media API for AI agents. Access Facebook, Instagram, TikTok, and more.
SocialAPIsHub social-media-api MCP Server (Model Context Protocol)
This MCP server provides a unified social media API for AI agents. It supports access to Facebook, Instagram, TikTok, and more, and is categorized under Model Context Protocol (MCP) and MCP server. The repository name is io.github.SocialAPIsHub/social-media-api, with topics spanning AI agents, LLM tools, and web scraping.
🛠️ Key Features
Unified social media API for AI agents
Social media access covering Facebook, Instagram, TikTok, and more
Includes MCP / MCP server support
Tagged for ads library, web-scraping, and social media
🚀 Use Cases
Integrate social media data into AI agent workflows
Use within LLM tools and MCP-based tool ecosystems
Retrieve or work with advertising/library-related information
⚡ Developer Benefits
Designed for MCP server environments
Emphasizes use with AI agents and LLM tools
Focus on social media integrations and web scraping
⚠️ Limitations
Supported platforms beyond Facebook, Instagram, and TikTok are not enumerated in the provided data.
🌐 Unified API - One interface for multiple platforms
🤖 AI-First - Built for Claude, Cursor, and AI agents
📊 Rich Data - Posts, comments, engagement metrics
🔍 Advanced Filtering - Time ranges, pagination
🎯 Simple Auth - No OAuth complexity
⚡ Fast - Global edge network
🔒 Secure - API keys stay local
🛠️ Available Tools
47 tools across Facebook and Instagram. Every tool maps 1:1 to a REST endpoint on api.socialapis.io — pricing notes in each tool description indicate per-call credit cost.
Facebook — Pages
facebook_get_page_id — Extract page ID from URL
facebook_get_page_details — Page info, followers, likes, category. Set exact_followers_count=true for the exact integer (charges 5 credits instead of 1)
facebook_get_page_posts — Fetch posts with after_time / before_time for date filtering. limit 3-9, charges scale per ceil(returned / 3)
Each prompt below is a real Claude Desktop session. Some of these are single-tool-call patterns ("get me X"); some require Claude to chain multiple calls + aggregate the results (noted where).
Single-call patterns (fast, cheap)
code
What's Nike's follower count on Facebook?
→ Uses facebook_get_page_details (1 credit)
Get the latest 9 posts from facebook.com/EngenSA
→ Uses facebook_get_page_posts with limit=9 (1-3 credits depending on actual returned count)
Show me the Meta ads currently running for "Apple Vision Pro" in Germany
→ Uses facebook_ads_search (1 credit)
Multi-call patterns (Claude orchestrates these — but it's slower + more expensive)
code
Compare engagement on Nike vs Adidas's last 9 Facebook posts
→ Claude calls facebook_get_page_posts twice (~2-6 credits total),
aggregates reactions/comments/shares per post, returns a comparison.
What are people saying in the comments on Coca-Cola's last 3 posts?
→ Claude calls facebook_get_page_posts (1 credit) then
facebook_get_post_comments 3 times (3 credits) and summarizes.
Show me marketplace listings for "PlayStation 5" under $400 in Berlin
→ Claude calls facebook_marketplace_city_coordinates (1 credit) +
facebook_marketplace_search with filters (1 credit).
What this MCP server does NOT do
Some queries look natural in a chat ("compare engagement over the last month") but require aggregations the API doesn't expose as a single tool yet. Claude can still answer them, but it'll fan out into many tool calls — which is slow + expensive.
Query shape
Why it's hard
"Engagement rate over the last 30 days" for a page
Requires fetching every post in the date range (paginated, limit capped at 9 per call) and computing engagement per post. Hits the LLM tool-call budget on busy pages.
"Compare engagement rates between Brand A, B, C over the last month"
Same problem, 3× — one paginated fetch per brand, then comparison math. Works for small windows; slow for "last month" on high-volume pages.
Historical archive older than what Facebook itself serves
We surface what Facebook makes publicly visible. Posts that scrolled off Facebook's visible feed aren't retrievable.
Not yet — on the roadmap as a future engagement-stats endpoint with built-in aggregation.
If your use case maps to one of these patterns and you want the aggregation pre-computed instead of LLM-orchestrated, contact support with the specific query — we're prioritizing the aggregation endpoint based on customer demand.
Advanced analytics — server-side aggregation endpoints (engagement-over-time, brand comparisons) so multi-call patterns become a single tool call
Real-time webhooks — push notifications on new posts / engagement thresholds
LangChain integration
Platform priorities shift based on customer demand. The fastest way to push something up the queue is to email support@socialapis.io or DM @socialapis on Telegram with the use case.
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
