Skip to main content
Glama

Social Media MCP Server

A Model Context Protocol (MCP) server that connects to multiple social media platforms, allowing users to create and publish content across platforms through natural language instructions.

Features

  • Natural Language Interface: Create posts for multiple platforms with simple instructions

  • Research Capabilities: Automatically research hashtags, trends, facts, and news

  • Multi-platform Support: Post to Twitter/X, Mastodon, and LinkedIn with platform-specific formatting

  • Content Generation: Generate engaging content using multiple AI models

  • Rate Limit Management: Handle API rate limits gracefully with queuing and fallbacks

  • Analytics: Track post performance and optimize content strategy

Related MCP server: PostWire

Getting Started

Prerequisites

  • Node.js (v18+)

  • npm or yarn

  • API keys for:

    • Twitter/X

    • Mastodon

    • LinkedIn

    • OpenAI and/or Anthropic (for content generation)

    • Brave Search (for research)

Installation

  1. Clone the repository:

git clone https://github.com/yourusername/social-media-mcp.git
cd social-media-mcp
  1. Install dependencies:

npm install
  1. Create a .env file with your API keys:

# Twitter API Credentials
TWITTER_API_KEY=your_api_key
TWITTER_API_SECRET=your_api_secret
TWITTER_BEARER_TOKEN=your_bearer_token
TWITTER_ACCESS_TOKEN=your_access_token
TWITTER_ACCESS_SECRET=your_access_secret
TWITTER_OAUTH_CLIENT=your_oauth_client
TWITTER_CLIENT_SECRET=your_client_secret

# Mastodon API Credentials
MASTODON_CLIENT_SECRET=your_client_secret
MASTODON_CLIENT_KEY=your_client_key
MASTODON_ACCESS_TOKEN=your_access_token

# LinkedIn API Credentials
LINKEDIN_CLIENT_ID=your_client_id
LINKEDIN_CLIENT_SECRET=your_client_secret
LINKEDIN_ACCESS_TOKEN=your_access_token

# AI API Keys
ANTHROPIC_API_KEY=your_anthropic_key
OPENAI_API_KEY=your_openai_key
BRAVE_API_KEY=your_brave_key

# Application Settings
LOG_LEVEL=info
CACHE_ENABLED=true
RATE_LIMIT_ENABLED=true
  1. Build the project:

npm run build
  1. Start the server:

npm start

MCP Integration

To use this MCP server with Claude or another MCP-compatible assistant, add it to your MCP settings:

{
  "mcpServers": {
    "social-media-mcp": {
      "command": "node",
      "args": ["path/to/social-media-mcp/build/index.js"],
      "env": {
        "TWITTER_API_KEY": "your_api_key",
        "TWITTER_API_SECRET": "your_api_secret",
        "TWITTER_BEARER_TOKEN": "your_bearer_token",
        "TWITTER_ACCESS_TOKEN": "your_access_token",
        "TWITTER_ACCESS_SECRET": "your_access_secret",
        "TWITTER_OAUTH_CLIENT": "your_oauth_client",
        "TWITTER_CLIENT_SECRET": "your_client_secret",
        "MASTODON_CLIENT_SECRET": "your_client_secret",
        "MASTODON_CLIENT_KEY": "your_client_key",
        "MASTODON_ACCESS_TOKEN": "your_access_token",
        "LINKEDIN_CLIENT_ID": "your_client_id",
        "LINKEDIN_CLIENT_SECRET": "your_client_secret",
        "LINKEDIN_ACCESS_TOKEN": "your_access_token",
        "ANTHROPIC_API_KEY": "your_anthropic_key",
        "OPENAI_API_KEY": "your_openai_key",
        "BRAVE_API_KEY": "your_brave_key"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Available Tools

create_post

Create and post content to social media platforms based on natural language instructions.

{
  "instruction": "Post about the latest AI developments in healthcare",
  "platforms": ["twitter", "mastodon", "linkedin"],
  "postImmediately": false
}

Get trending topics from social media platforms.

{
  "platform": "twitter",
  "category": "technology",
  "count": 5
}

research_topic

Research a topic using Brave Search and Perplexity.

{
  "topic": "artificial intelligence ethics",
  "includeHashtags": true,
  "includeFacts": true,
  "includeTrends": true,
  "includeNews": true
}

Development

Project Structure

social-media-mcp/
├── src/
│   ├── index.ts                 # Entry point
│   ├── config/                  # Configuration
│   ├── types/                   # TypeScript type definitions
│   ├── core/                    # Core orchestration logic
│   ├── nlp/                     # Natural language processing
│   ├── research/                # Research engine
│   │   ├── brave/               # Brave Search integration
│   │   ├── perplexity/          # Perplexity integration
│   │   └── aggregator/          # Research result aggregation
│   ├── content/                 # Content generation
│   │   ├── strategies/          # AI model strategies
│   │   ├── formatter/           # Platform-specific formatting
│   │   └── templates/           # Content templates
│   ├── platforms/               # Social media platform integrations
│   │   ├── twitter/             # Twitter API integration
│   │   └── mastodon/            # Mastodon API integration
│   ├── analytics/               # Analytics engine
│   ├── rate-limit/              # Rate limit management
│   └── utils/                   # Utility functions
├── memory-bank/                 # Project documentation
├── build/                       # Compiled JavaScript
├── .env                         # Environment variables
├── package.json                 # Dependencies and scripts
└── tsconfig.json                # TypeScript configuration

Scripts

  • npm run build: Build the project

  • npm run dev: Run in development mode with hot reloading

  • npm start: Start the production server

  • npm test: Run tests

  • npm run lint: Run linting

  • npm run format: Format code

Utility Scripts

The scripts directory contains utility scripts for the Social Media MCP Server:

  • scripts/linkedin-oauth.js: Handles the OAuth 2.0 flow for LinkedIn to obtain an access token

    • Usage: cd scripts && npm install && npm run linkedin-oauth

    • See scripts/README.md for more details

Documentation

The documentation directory contains detailed documentation for each social media platform integration:

License

This project is licensed under the ISC License.

Acknowledgements

Available Tools

3 tools
create_postC

Create and post content to social media platforms based on natural language instructions

Inputs: instruction (required), platforms, postImmediately, conversationId, +4 more.

research_topicC

Research a topic using Brave Search and Perplexity

Inputs: topic (required), includeHashtags, includeFacts, includeTrends, +1 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.1/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: create_post handles content creation, get_trending_topics retrieves trending information, and research_topic performs topic research using external search tools. There is no overlap in functionality, making tool selection straightforward for an agent.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern (create_post, get_trending_topics, research_topic), using snake_case throughout. This predictability enhances readability and usability for agents.

    Tool Count2/5

    With only 3 tools, the server feels under-scoped for a social media domain. Key operations like reading posts, updating/deleting content, or interacting with comments are missing, limiting the server's utility for comprehensive social media tasks.

    Completeness2/5

    The toolset is severely incomplete for social media operations. It lacks basic CRUD functionality (e.g., no read, update, or delete for posts), interaction tools (e.g., like, comment, share), and platform-specific features, leaving significant gaps that will hinder agent workflows.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Official MCP server for PostEverywhere (posteverywhere.ai/social-media-scheduler). Let Claude, ChatGPT, Cursor or any MCP client schedule and publish posts to 13 platforms: Instagram, TikTok, YouTube, LinkedIn, Facebook, X, Threads, Pinterest, Bluesky, Telegram, Discord, WordPress and Google Business Profile. 40 tools: best-time scheduling, threads, cross-posting, campaigns, analytics.
      33
      289 npm
      7
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      One prompt, a native post per network, published or scheduled by your agent: TikTok, Instagram, Facebook, YouTube, LinkedIn, Bluesky, Mastodon, Telegram, Discord, Slack, Nostr, X, WordPress, Dev.to, Hashnode. 22 tools incl. plan_week, bulk_schedule, analytics and TikTok video quality check. Priced per brand, not per channel; API + MCP on the free plan. Hosted: postwire.io/api/mcp
      22
      87 npm
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables AI assistants to manage social media publishing across platforms like LinkedIn, Twitter, Facebook, Instagram, Threads, and Bluesky.
      7
      54 npm
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      One AI studio for blogs, social posts, emails, ads and product listings: written in your brand's voice, fact-checked, designed and scheduled. A remote MCP server for Claude, ChatGPT, Cursor and other agents, with OAuth sign-in or an API key; every post waits for your go-ahead.
      MIT