Read public X posts with no account or key: Articles as Markdown, video transcripts, posts.
Scored across 4 tools
Each tool targets a distinct content type and action: reading a post, reading an article, retrieving an existing video transcript, or creating a new transcript. The descriptions explicitly cross-reference each other, e.g. read_x_article for Articles and transcribe_x_video when no transcript exists, eliminating ambiguity.
All names follow a consistent snake_case verb_noun pattern with an x_ prefix: get_x_video_transcript, read_x_article, read_x_post, transcribe_x_video. Verb variation (get/read/transcribe) reflects genuine action differences rather than inconsistency.
Four tools is well-scoped for a focused X content-extraction toolkit. Each tool covers a distinct content type and none feels redundant or missing for the stated reading/transcription purpose.
The surface fully covers single-post content extraction: posts, Articles, video transcripts, and transcription of uncaptioned video. Minor gaps remain around discovery and context, such as search, user timelines, or thread/reply retrieval, but core workflows are covered.
Returns the transcript of the video in an X (Twitter) post: X's own captions when they exist, or a transcript x-toolkit made earlier. If there is none yet, it says so; call transcribe_x_video to make one.
Inputs: url (required), format.
Returns an X (Twitter) Article as Markdown with images in place. X only shows Articles to signed-in readers, so fetching the link directly gets a login page. Pass the link of the post the Article was published in. Optionally translate it with lang.
Inputs: url (required), lang.
Returns a single X (Twitter) post as Markdown: author, date, text, the quoted post, image links and counts. For an Article use read_x_article; for a video's words use get_x_video_transcript.
Inputs: url (required).
Transcribes the video in an X post that has no captions, one part (about 108 seconds of audio) per call. Start with part 0. Each call says whether to call again with the next part; the last one returns the transcript. The transcript is saved, so get_x_video_transcript works for it afterwards. Videos up to 15 minutes. Only text is stored, never video or audio.
Inputs: url (required), part, format.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Read public X posts and full X Articles as clean Markdown. Free, no X API key.
Read public X (Twitter) posts, threads and X Articles as clean Markdown. Read-only, no auth.
Read public Twitter/X data: tweets, profiles, followers, search. No X developer account.
X/Twitter search, posts, comments, user profiles, user posts/replies and video transcripts.
Add one secure layer between your agents and this server.
