Research X (Twitter) from Claude or ChatGPT with the buzzabout MCP.

Ask Claude or ChatGPT how people on X react to your launch, your competitors or your category. buzzabout finds the relevant posts, drops the noise, reads the replies and hands back the answer with sources.

Try for free Add to Claude or ChatGPT

Free trial with 1,000 credits. Copy page as Markdown Open in Claude

Example
How do people on X feel about AI-generated ads?
buzzaboutcollect_mentionsdetect_patternsquery

I read 300 recent posts on AI-generated ads and dropped the off-topic ones before billing. Sentiment runs 58% negative, driven by cheap-looking creative ("If you can't pay a designer, why would I trust the product?") and calls for disclosure ("Just label it"), while the upside people cite is small brands saving on production. Want the most-liked replies under each theme?

3.5 minmedian run time to fully analyzed posts
99%of research runs complete
7platforms in one connection
$49to start, MCP included

Questions you can ask about X (Twitter)

Ask in plain English. Get answers with sources.

“How did our launch land on X?”

Sentiment, emotions and topics on every on-topic post, with the lines that set the tone.

“What are the strongest objections to our category?”

Negative posts grouped into named themes, each with the posts and replies behind it.

“Which posts in our space got the most reposts this month?”

Posts ranked by reposts, likes and replies, with engagement rate worked out the same way for each.

“What do people ask about our product on X?”

Questions pulled from posts and up to 100 replies per post, grouped and counted.

“Who is talking about our category on X?”

Interests, countries and brand affinities of the people replying, quoting and reposting, in aggregate, on Pro and up.

“Is the conversation about our brand getting better or worse?”

Sentiment score charted by day or week across every post.

What your AI gets back

Every X (Twitter) post arrives transcribed, labeled and ready to use. Fifteen MCP tools do the work.

One X (Twitter) post, as your AI gets itBlue = added by buzzabout
{
  "source": "x",
  "url": "https://x.com/example_dev/status/1985...",
  "text": "AI coding agents: great at small fixes, bad at design.",
  "summary": "Developer finds AI agents good for fixes, not design.",
  "hooks": [
    {
      "type": "Bold Claim / Contrarian",
      "text": "AI coding agents: great at small fixes"
    }
  ],
  "content_topics": [
    {
      "text": "AI coding agents"
    },
    {
      "text": "code review"
    }
  ],
  "sentiment": {
    "positive": "0.40",
    "neutral": "0.35",
    "negative": "0.25"
  },
  "emotions": {
    "surprise": "0.30",
    "joy": "0.25",
    "neutral": "0.45"
  },
  "tone_of_voice": {
    "text": "casual",
    "evidence": "bad at design"
  },
  "narrative_structure": {
    "text": "contrast",
    "evidence": "great at small fixes, bad at design"
  },
  "cta": {
    "text": "none",
    "evidence": null
  },
  "media": [
    {
      "type": "image",
      "description": "Screenshot of a code diff with review notes"
    }
  ],
  "created_at": 1793577600,
  "dataset_run_at": 1793750400,
  "content_analyzed_at": 1793750700,
  "author": {
    "title": "@example_dev",
    "headline": "Example Dev"
  },
  "num_views": 23800,
  "num_likes": 412,
  "num_comments": 57,
  "num_shares": 38,
  "engagement_rate": "0.021",
  "category": "technology_and_computing",
  "sentiment_score": "0.15",
  "language": "en"
}

15 MCP tools

Research

  • askAsk a research question in plain English; get a cited answer.
  • get_messageRead the research agent's answer as it lands.

Collect

  • collect_mentionsPreview a topic, then collect and analyze the posts.
  • ingest_mentionSave and analyze one public post by URL.
  • get_runFollow any run's progress, with long-polling.
  • get_save_mention_statusTrack a saved post's analysis.

Analyze

  • queryAsk your data anything: counts, themes, trends, comments, audience.
  • list_mentionsRead collected posts with all their AI fields.
  • detect_patternsGroup posts into 2 to 15 named themes.
  • collect_audienceProfile the people commenting, in aggregate (Pro and up).
  • renderShow answers as interactive charts and tables.

Track and manage

  • list_tracking_agentsSee your scheduled topic trackers.
  • get_tracking_agentRead one tracker and what it found.
  • list_collectionsSee everything you have collected.
  • get_meCheck your plan and credit balance.
Every field in a post

Transcript and on-screen text

  • media[].transcriptionThe spoken words in videos, transcribed.
  • media[].on_screen_textText burned into video frames, read by OCR.
  • media[].descriptionWhat the photo or video shows, described by AI.

Hooks and format

  • hooksHook type plus the exact opening line.
  • narrative_structurePost shape, with the quote that shows it.
  • ctaThe call to action, with evidence.
  • content_intentionInform, entertain, sell or engage.
  • categoryContent category, such as technology_and_computing.

Topics and questions

  • summaryA short summary of the post.
  • content_topicsThe topics it covers.
  • questionsQuestions asked in the post.
  • mentioned_brandsBrands named in the text or shown in the media.
  • entitiesPeople, places, events and organizations named; brands are in mentioned_brands.

Sentiment and tone

  • sentimentPositive, neutral and negative shares.
  • sentiment_scoreOne number from negative to positive.
  • emotionsJoy, surprise, anger, sadness, fear, disgust, neutral.
  • tone_of_voiceTone label with the line that sets it.

Engagement

  • num_viewsView count from X, estimated from engagement when X shows none.
  • num_likesLikes.
  • num_commentsReplies.
  • num_sharesReposts.
  • engagement_rate(likes + replies + reposts) / views, computed for you.

Comments

  • comments[].bodyThe reply text.
  • comments[].num_likesLikes on the reply.
  • comments[].num_repliesHow many replies it drew.
  • comments[].created_atWhen it was posted.
  • comments[].sentimentHow each comment feels, scored (via query).

Read comments through MCP query or buzzabout__ask. They are not in list_mentions or the REST response yet.

Also in every record: url, text, author.title, author.headline, author.avatar, media[].version_list, media[].version_list[].duration_millis, media[].cover_image, created_at, dataset_run_at, content_analyzed_at.

How it compares

Other data providers give you raw posts. buzzabout gives you answers.

CapabilitybuzzaboutOther data providers
What you get backYesPosts already read, labeled and grouped into themesNoRaw posts
Works in Claude, ChatGPT and other AI agentsYesOne MCP connection, every planYesRaw-data MCP servers
All 7 platforms in one requestYesOne question covers all 7PartlyOne scraper per platform
Off-topic posts filtered, never billedYesAI check on every postNoYou pay for every record returned
Transcripts and on-screen textYesEvery video, includedPartlyPaid add-ons on some tools
Hooks, topics, sentiment and toneYesOn every postNoBring your own AI
Comments with every postYesUp to 100 per post, includedPartlySeparate scraper, billed per comment
Themes across many postsYes2 to 15 named themes per questionNoNone
PriceStarting at $49, everything includedFrom about $472 a month for the full stack

Everything included, starting at $49

Bought separately, the same stack costs about $472 a month, before anyone builds anything.

2,000
Bought separately
$472
buzzabout
$49
Bought separately$472a month
buzzabout$49Starter, first month

What buzzabout includes

  • DataPosts, comments and transcripts from 7 platforms
  • ProcessingHooks, pains, formats and sentiment on every post
  • Research toolsThemes, audiences, trends and briefs
  • StorageEvery collection kept and shareable by link
  • WorkflowsListening agents that run on a schedule
  • MemoryYour past research, ready for the next question
  • IntegrationsClaude, ChatGPT, Slack alerts and the API

Two ways to use it

MCP on every plan. REST API on Business.

Marketers

In Claude or ChatGPT

Add buzzabout as a connector and ask in plain English. That's it.

  1. Start your free trial.
  2. In Claude or ChatGPT, add a custom connector with https://mcp.buzzabout.ai/mcp and sign in.
  3. Ask about X (Twitter).
Growth engineers

In Claude Code or your own agent

Install the MCP server and let Claude Code build on it: digests, dashboards, alerts.

  1. Run claude mcp add --transport http buzzabout https://mcp.buzzabout.ai/mcp.
  2. Tell Claude Code what to build, for example a weekly digest of X (Twitter) posts about your competitors.
  3. Schedule it with tracking agents and webhooks. The REST API is there on Business.
1. In Claude, add a custom connector.
2. URL:  https://mcp.buzzabout.ai/mcp
3. Sign in, then ask:

   "What do people on X (Twitter) say about
    reactions to AI coding agents?"

Pricing

Every plan includes the MCP and the full analysis.

Starter

$49first month, then $98/mo

2,000 credits a month. Up to 250 posts per research.

Try for free

Pro

$178/month

5,000 credits a month. Audience research. Up to 1,000 posts per research.

Try for free

Business

$450/month

20,000 credits a month. REST API. Unlimited listening agents.

Try for free

Free trial with 1,000 credits. A card is needed to sign up. See pricing.

Questions

How much does the X API cost in 2026?

X sells its API pay-per-use only. Reading a post costs $0.005, or $5 per 1,000 posts, and reading a user costs $0.010. Pay-per-use stops at 3 million post reads a month; above that you need Enterprise. Every read is billed, on topic or not, and returns the raw post with no analysis. buzzabout bills only for posts that fit your question, with the analysis included, and you ask for them from Claude in plain English.

What is the best X (Twitter) MCP for research?

buzzabout. Connect it to Claude or ChatGPT and you get only the X posts that fit your question, scored for sentiment and labeled for topics and questions, with replies and the transcript of any video, through one connection that covers six other platforms. A typical run is ready in 3.5 minutes, 99% of runs complete, and you pay only for posts you keep.

Can I get sentiment for tweets through an API?

Yes. buzzabout scores each X post for sentiment and emotion, labels its tone with the quote that sets it, and adds topics, questions and the brands it mentions. Ask Claude to split a topic by sentiment, chart it by week or pull the most negative replies, all in plain English.

Can I get replies to a tweet through an API?

Yes. For every post it collects, buzzabout keeps up to 100 replies as a flat list at no extra cost, with likes, reply counts, timestamps and sentiment. Ask Claude or ChatGPT about them in plain English, or query them through the MCP.

Why not just use a scraper or another data provider for X?

A scraper hands you every X post that matches a keyword, spam and off-topic ones included, and stops. Relevance filtering, transcription, labeling and storage are separate tools you buy, connect and maintain. Add themes, scheduled runs, memory and integrations and the full stack starts at about $472 a month, before anyone builds anything. buzzabout includes all of it, starting at $49, through one connection your agent already speaks. Some data providers cannot even search X by keyword; they need post or profile URLs first.

How much does buzzabout cost for X (Twitter) research?

Starting at $49 for your first month on Starter, then $98 a month. Each post you keep costs one credit, with the analysis included. See pricing.

Does it work in ChatGPT?

Yes. Add buzzabout as a custom connector in ChatGPT with https://mcp.buzzabout.ai/mcp and sign in. Custom connectors depend on your ChatGPT plan.

Do I pay for off-topic or duplicate X (Twitter) posts?

No. You pay only for the posts you keep.

Do I need to code?

No. Add buzzabout to Claude or ChatGPT and ask in plain English. Growth engineers can use the same MCP in Claude Code or Cursor.

How do I start?

Start a free trial with 1,000 credits, add buzzabout to Claude or ChatGPT and ask your first question.

Other platforms

TikTok MCP

Videos, transcripts, hooks

Instagram MCP

Posts, reels, transcripts

YouTube MCP

Videos, captions, sentiment

LinkedIn MCP

B2B posts, reactions, topics

Facebook MCP

Pages, groups, video transcripts

Try it on your own topic

Free trial. Works in Claude and ChatGPT.

Try for free Add to Claude or ChatGPT
Free trial with 1,000 credits · MCP on every plan