Agent Twitter Client MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Port to run the MCP server on (default: 3000) | |
| NODE_ENV | No | Environment (development, production) | |
| LOG_LEVEL | No | Logging level (error, warn, info, debug) | |
| AUTH_METHOD | No | Authentication method to use: 'cookies', 'credentials', or 'api' | |
| TWITTER_EMAIL | No | Your Twitter email address (optional for credentials authentication) | |
| TWITTER_API_KEY | No | Your Twitter API key (for API authentication) | |
| TWITTER_COOKIES | No | JSON array of Twitter cookies strings (required for cookie authentication). Essential cookies are auth_token, ct0, and twid. | |
| TWITTER_PASSWORD | No | Your Twitter password (for credentials authentication) | |
| TWITTER_USERNAME | No | Your Twitter username (for credentials authentication) | |
| TWITTER_2FA_SECRET | No | Your Twitter 2FA secret (required if 2FA is enabled for credentials authentication) | |
| TWITTER_ACCESS_TOKEN | No | Your Twitter access token (for API authentication) | |
| TWITTER_API_SECRET_KEY | No | Your Twitter API secret key (for API authentication) | |
| TWITTER_ACCESS_TOKEN_SECRET | No | Your Twitter access token secret (for API authentication) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_user_tweetsB | Fetch tweets from a specific user |
| get_tweet_by_idB | Fetch a specific tweet by ID |
| search_tweetsC | Search for tweets by keyword |
| send_tweetC | Post a new tweet |
| send_tweet_with_pollC | Post a tweet with a poll |
| like_tweetC | Like a tweet |
| retweetB | Retweet a tweet |
| quote_tweetC | Quote a tweet |
| get_user_profileC | Get a user's profile information |
| follow_userC | Follow a Twitter user |
| get_followersC | Get a user's followers |
| get_followingC | Get users a user is following |
| grok_chatB | Chat with Grok via Twitter |
| health_checkA | Check the health of the Twitter MCP server |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 14 tools
Every tool has a clearly distinct purpose with no ambiguity. Each tool targets a specific Twitter action (like, retweet, quote, follow) or data retrieval operation (get followers, get tweets, search), and the descriptions make their unique functions immediately apparent. There is no overlap that would cause confusion or misselection.
The naming is mostly consistent with a clear verb_noun pattern (e.g., follow_user, get_followers, like_tweet), but there are minor deviations. For example, 'grok_chat' and 'health_check' follow the pattern but stand out as non-core Twitter actions, and 'send_tweet' and 'send_tweet_with_poll' could be more aligned (e.g., 'post_tweet'). Overall, the naming is readable and predictable.
With 14 tools, this is well-scoped for a Twitter client server, covering core social media interactions and data access. Each tool earns its place by addressing a specific need, such as posting, liking, searching, or retrieving user information, without being overly bloated or too sparse for the domain.
The tool set provides comprehensive coverage for Twitter operations, including CRUD-like actions (send, like, retweet) and data retrieval (get tweets, search, profile). Minor gaps exist, such as no tools for deleting tweets, managing lists, or handling direct messages, but agents can work around these with the available tools for core workflows.