social-media-mcp
About
A Model Context Protocol (MCP) server for managing social media posts, currently supporting X (formerly Twitter).
Details
- Author
- angheljf
- Repository
- angheljf/social-media-mcp
- GitHub stars
- 8
- Downloads
- 3
- License
- MIT License
- Categories
- Media, Developer Tools
Jump to
- Post messages to X (Twitter)
- Create threads on X
- Reply to existing threads
- List X posts with filtering options
- Platform information endpoints
Setting up with Highlight
Follow these steps to add this server as a custom Highlight plugin:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
social-media-mcpCommand (node, npx, python, etc.)npxArguments-
Argument 1
-y -
Argument 2
@highlight/mcp-server
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
-
Argument 1
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
To install Social Media Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install social-media-server --client claude
1. Clone the repository
2. Install dependencies:
npm install
3. Create a .env file with your Twitter credentials:
TWITTER_API_KEY=your_api_key
TWITTER_API_SECRET=your_api_secret
TWITTER_ACCESS_TOKEN=your_access_token
TWITTER_ACCESS_SECRET=your_access_secret
post_to_x
Post a message to X. Required: content (string). Optional: threadId (string).
create_x_thread
Create a new thread on X. Required: content (string).
list_x_post
List X posts with optional filtering. Optional: limit (number), threadId (string).
- post_to_x - Post a message to X
- Required: content (string)
- Optional: threadId (string)
- create_x_thread - Create a new thread on X
- Required: content (string)
- list_x_post - List X posts with optional filtering
- Optional: limit (number)
- Optional: threadId (string)
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"social-media-mcp": {
"env": {},
"args": [
"-y",
"@highlight/mcp-server"
],
"command": "npx"
}
}
}
Linux
{
"env": [],
"args": [
"-y",
"@highlight/mcp-server"
],
"command": "npx"
}
Macos
{
"env": [],
"args": [
"-y",
"@highlight/mcp-server"
],
"command": "npx"
}
Windows
{
"env": [],
"args": [
"/c",
"npx",
"-y",
"@highlight/mcp-server"
],
"command": "cmd"
}
Social Media Server
A Model Context Protocol (MCP) server for managing social media posts, currently supporting X (formerly Twitter).

<a href="https://glama.ai/mcp/servers/55bvn41dtb">
</a>
Features
- Post messages to X (Twitter)
- Create threads on X
- Reply to existing threads
- List X posts with filtering options
- Platform information endpoints
Prerequisites
- Node.js 16 or higher
- Twitter API credentials
- API Key
- API Secret
- Access Token
- Access Secret
Installation
Installing via Smithery
To install Social Media Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install social-media-server --client claude
Manual Installation
1. Clone the repository 2. Install dependencies:npm install
3. Create a .env file with your Twitter credentials:
TWITTER_API_KEY=your_api_key
TWITTER_API_SECRET=your_api_secret
TWITTER_ACCESS_TOKEN=your_access_token
TWITTER_ACCESS_SECRET=your_access_secret
Building
To build the project, run:
npm run build
Available Tools
- post_to_x - Post a message to X
- Required: content (string)
- Optional: threadId (string)
- create_x_thread - Create a new thread on X
- Required: content (string)
- list_x_post - List X posts with optional filtering
- Optional: limit (number)
- Optional: threadId (string)
Resources
The server provides platform information via:
- socialmedia://platforms/x
Development
The project uses TypeScript and follows the Model Context Protocol specification. The main server implementation is in index.ts, with types defined in types.ts.
License
This project is licensed under the MIT License
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.





