X Twitter Integration
STDIOMCP server for interacting with Twitter via AI tools through natural language commands.
MCP server for interacting with Twitter via AI tools through natural language commands.
A Model Context Protocol (MCP) server for interacting with Twitter (X) via AI tools. This server allows you to fetch tweets, post tweets, search Twitter, manage followers, and more, all through natural language commands in AI Tools.
uv
or pip
for Python dependencies.To install X (Twitter) MCP server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @rafaljanicki/x-twitter-mcp-server --client claude
The easiest way to install x-twitter-mcp
is via PyPI:
pip install x-twitter-mcp
If you prefer to install from the source repository:
Clone the Repository:
git clone https://github.com/rafaljanicki/x-twitter-mcp-server.git cd x-twitter-mcp-server
Set Up a Virtual Environment (optional but recommended):
python -m venv .venv source .venv/bin/activate # On Windows: .venv\Scripts\activate
Install Dependencies:
Using uv
(recommended, as the project uses uv.lock
):
uv sync
Alternatively, using pip
:
pip install .
Configure Environment Variables:
.env
file in the project root (you can copy .env.example
if provided).TWITTER_API_KEY=your_api_key
TWITTER_API_SECRET=your_api_secret
TWITTER_ACCESS_TOKEN=your_access_token
TWITTER_ACCESS_TOKEN_SECRET=your_access_token_secret
TWITTER_BEARER_TOKEN=your_bearer_token
You can run the server in two ways:
The project defines a CLI script x-twitter-mcp-server
.
If installed from PyPI:
x-twitter-mcp-server
If installed from source with uv
:
uv run x-twitter-mcp-server
If you installed from source and prefer to run the server using FastMCP’s development mode:
fastmcp dev src/x_twitter_mcp/server.py
The server will start and listen for MCP connections. You should see output like:
Starting TwitterMCPServer...
To use this MCP server with Claude Desktop, you need to configure Claude to connect to the server. Follow these steps:
Claude Desktop uses Node.js to run MCP servers. If you don’t have Node.js installed:
node --version
Claude Desktop uses a claude_desktop_config.json
file to configure MCP servers.
%APPDATA%\Claude\claude_desktop_config.json
~/Library/Application Support/Claude/claude_desktop_config.json
If the file doesn’t exist, create it.
Edit claude_desktop_config.json
to include the x-twitter-mcp
server. Replace /path/to/x-twitter-mcp-server
with the actual path to your project directory (if installed from source) or the path to your Python executable (if installed from PyPI).
If installed from PyPI:
{ "mcpServers": { "x-twitter-mcp": { "command": "x-twitter-mcp-server", "args": [], "env": { "PYTHONUNBUFFERED": "1", "TWITTER_API_KEY": "your_api_key", "TWITTER_API_SECRET": "your_api_secret", "TWITTER_ACCESS_TOKEN": "your_access_token", "TWITTER_ACCESS_TOKEN_SECRET": "your_access_token_secret", "TWITTER_BEARER_TOKEN": "your_bearer_token" } } } }
If installed from source with uv
:
{ "mcpServers": { "x-twitter-mcp": { "command": "uv", "args": [ "--directory", "/path/to/x-twitter-mcp-server", "run", "x-twitter-mcp-server" ], "env": { "PYTHONUNBUFFERED": "1" } } } }
"command": "x-twitter-mcp-server"
: Uses the CLI script directly if installed from PyPI."env"
: If installed from PyPI, you may need to provide environment variables directly in the config (since there’s no .env
file). If installed from source, the .env
file will be used."env": {"PYTHONUNBUFFERED": "1"}
: Ensures output is unbuffered for better logging in Claude.x-twitter-mcp
, such as post_tweet
, search_twitter
, get_user_profile
, etc.You can now interact with Twitter using natural language in Claude Desktop. Here are some example prompts:
Fetch a User Profile:
Get the Twitter profile for user ID 123456.
Claude will call the get_user_profile
tool and return the user’s details.
Post a Tweet:
Post a tweet saying "Hello from Claude Desktop! #MCP"
Claude will use the post_tweet
tool to post the tweet and confirm the action.
Search Twitter:
Search Twitter for recent tweets about AI.
Claude will invoke the search_twitter
tool and return relevant tweets.
Get Trends:
What are the current trending topics on Twitter?
Claude will use the get_trends
tool to fetch trending topics.
When prompted, grant Claude permission to use the MCP tools for the chat session.
Below is a list of all tools provided by the x-twitter-mcp
server, along with example executions in Claude Desktop using natural language prompts.
get_user_profile
Get the Twitter profile for user ID 123456789.
Claude will return the user’s profile details, including ID, name, username, profile image URL, and description.get_user_by_screen_name
Get the Twitter user with screen name "example_user".
Claude will return the user’s profile details.get_user_by_id
Fetch the Twitter user with ID 987654321.
Claude will return the user’s profile details.get_user_followers
Get the followers of user ID 123456789, limit to 50.
Claude will return a list of up to 50 followers.get_user_following
Who is user ID 123456789 following? Limit to 50 users.
Claude will return a list of up to 50 users.get_user_followers_you_know
Get common followers for user ID 123456789, limit to 50.
Claude will return a list of up to 50 common followers (simulated by filtering followers).get_user_subscriptions
Get the subscriptions for user ID 123456789, limit to 50.
Claude will return a list of up to 50 users (using following as a proxy for subscriptions).post_tweet
Post a tweet saying "Hello from Claude Desktop! #MCP"
Claude will post the tweet and return the tweet details.delete_tweet
Delete the tweet with ID 123456789012345678.
Claude will delete the tweet and confirm the action.get_tweet_details
Get details for tweet ID 123456789012345678.
Claude will return the tweet’s details, including ID, text, creation date, and author ID.create_poll_tweet
Create a poll tweet with the question "What's your favorite color?" and options "Red", "Blue", "Green" for 60 minutes.
Claude will create the poll tweet and return the tweet details.vote_on_poll
Vote "Blue" on the poll in tweet ID 123456789012345678.
Claude will return a mock response (since Twitter API v2 doesn’t support poll voting).favorite_tweet
Like the tweet with ID 123456789012345678.
Claude will favorite the tweet and confirm the action.unfavorite_tweet
Unlike the tweet with ID 123456789012345678.
Claude will unfavorite the tweet and confirm the action.bookmark_tweet
Bookmark the tweet with ID 123456789012345678.
Claude will bookmark the tweet and confirm the action.delete_bookmark
Remove the bookmark for tweet ID 123456789012345678.
Claude will remove the bookmark and confirm the action.delete_all_bookmarks
Delete all my Twitter bookmarks.
Claude will delete all bookmarks and confirm the action.get_timeline
Show my Twitter For You timeline, limit to 20 tweets.
Claude will return up to 20 tweets from your For You timeline.get_latest_timeline
Show my Twitter Following timeline, limit to 20 tweets.
Claude will return up to 20 tweets from your Following timeline.search_twitter
Search Twitter for recent tweets about AI, limit to 10.
Claude will return up to 10 recent tweets about AI.get_trends
What are the current trending topics on Twitter? Limit to 10.
Claude will return up to 10 trending topics.get_highlights_tweets
Get highlighted tweets from user ID 123456789, limit to 20.
Claude will return up to 20 tweets from the user’s timeline (simulated as highlights).get_user_mentions
Get tweets mentioning user ID 123456789, limit to 20.
Claude will return up to 20 tweets mentioning the user.Server Not Starting:
.env
file has all required Twitter API credentials (if installed from source).claude_desktop_config.json
or your shell.x-twitter-mcp-server
.uv
or your Python executable is correctly installed and accessible.Claude Not Detecting the Server:
claude_desktop_config.json
is correct.command
and args
point to the correct executable and script.Rate Limit Errors:
Syntax Warnings:
SyntaxWarning
messages from Tweepy, they are due to docstring issues in Tweepy with Python 3.13. The server includes a warning suppression to handle this.Contributions are welcome! Please open an issue or submit a pull request on the GitHub repository.
This project is licensed under the MIT License. See the LICENSE
file for details.