“What do customers ask each other in Facebook groups about our category?”
The questions asked in each post, near verbatim, grouped into named themes with post counts.
Research Facebook from Claude or ChatGPT with the buzzabout MCP.
Ask Claude or ChatGPT what people say in public Facebook groups and on pages you do not run. buzzabout finds the relevant posts, transcribes the videos, reads the comments and hands back the answer with sources.
Free trial with 1,000 credits. Copy page as Markdown Open in Claude
What do first-time home buyers ask each other in Facebook groups?
buzzaboutcollect_mentionsdetect_patternsquery
I read 250 recent public Facebook posts about buying a first home, plus their comments. Three questions keep coming back: what it costs beyond the down payment ("Nobody told me about closing costs"), whether to get pre-approved before viewing homes and which inspection findings are deal breakers. The mood is anxious but hopeful. Want the posts and comments behind each question?
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 Facebook
Ask in plain English. Get answers with sources.
“What does our competitor post on its Facebook page, and what works?”
That page's posts with likes, comments and shares, real views on video, and the hook and tone of each.
“Which brands do members of this group recommend?”
Brands named in text, speech or on screen, counted, with the sentiment of the posts that name them.
“What do the top video posts in our niche say in the first few seconds?”
Transcripts, on-screen text and opening hooks of video posts, sorted by real views.
“How do people feel about our brand on Facebook this month?”
Sentiment and emotions on every post, with the lines that set the tone.
“What do commenters complain about under posts on this topic?”
Comment text with likes, reply counts and sentiment, so the complaints stand out.
What your AI gets back
Every Facebook post arrives transcribed, labeled and ready to use. Fifteen MCP tools do the work.
{
"source": "facebook",
"url": "https://www.facebook.com/examplehometeam/videos/12...",
"text": "3 mistakes first-time buyers make (save this)",
"summary": "Agent lists three costly mistakes new buyers make.",
"hooks": [
{
"type": "Social Proof / Authority",
"text": "After 400 closings, I see this every week"
}
],
"content_topics": [
{
"text": "mortgage pre-approval"
},
{
"text": "home inspections"
}
],
"questions": [
{
"text": "Do I need pre-approval before viewing homes?"
}
],
"sentiment": {
"positive": "0.62",
"neutral": "0.30",
"negative": "0.08"
},
"emotions": {
"joy": "0.40",
"fear": "0.30",
"neutral": "0.30"
},
"tone_of_voice": {
"text": "encouraging and professional",
"evidence": "You have got this"
},
"narrative_structure": {
"text": "problem-agitate-solution",
"evidence": "Here is how to avoid it"
},
"cta": {
"text": "comment/engage",
"evidence": "Drop your questions below"
},
"media": [
{
"type": "video",
"version_list": [
{
"duration_millis": 48200
}
],
"transcription": "Mistake one: house hunting before pre-approval...",
"on_screen_text": "MISTAKE #1: NO PRE-APPROVAL",
"description": "Agent talks to camera outside a family home"
}
],
"created_at": 1793433600,
"dataset_run_at": 1793836800,
"content_analyzed_at": 1793837100,
"author": {
"title": "Example Home Team",
"headline": "examplehometeam"
},
"num_views": 52000,
"are_views_estimated": false,
"num_likes": 1300,
"num_comments": 210,
"num_shares": 340,
"engagement_rate": "0.036",
"category": "real_estate",
"content_intention": "promotional",
"sentiment_score": "0.54",
"music_genre": "pop",
"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. Not for Facebook posts.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 a video, transcribed.media[].on_screen_textText burned into the frames, read by OCR.media[].descriptionWhat the video or image shows, described by AI.
Hooks and format
hooksHook type plus the exact opening line.narrative_structureStory shape, with the quote that shows it.ctaThe call to action, with evidence.content_intentionWhy it was posted: to engage, persuade or promote.music_genreGenre of the background track, on video posts.
Topics and questions
summaryA short summary of the post.content_topicsThe topics it covers.questionsQuestions asked in the post.mentioned_brandsBrands named in speech, text or on screen.entitiesPeople, places, events and organizations named; brands are inmentioned_brands.languageThe post's language. Quotes and transcripts stay as written.
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_viewsReal views on video posts, an estimate on the rest.are_views_estimatedTells you which of the two you have, post by post.num_likesLikes and reactions.num_commentsComment count.num_sharesShares.engagement_rate(likes + comments + shares) / views, computed for you.
Comments
comments[].bodyThe comment text.comments[].author_nameThe commenter's name.comments[].num_likesLikes on the comment.comments[].created_atWhen it was posted.comments[].sentimentHow each comment feels, scored (viaquery).
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.
| Capability | buzzabout | Other data providers |
|---|---|---|
| What you get back | YesPosts already read, labeled and grouped into themes | NoRaw posts |
| Works in Claude, ChatGPT and other AI agents | YesOne MCP connection, every plan | YesRaw-data MCP servers |
| All 7 platforms in one request | YesOne question covers all 7 | PartlyOne scraper per platform |
| Off-topic posts filtered, never billed | YesAI check on every post | NoYou pay for every record returned |
| Transcripts and on-screen text | YesEvery video, included | PartlyPaid add-ons on some tools |
| Hooks, topics, sentiment and tone | YesOn every post | NoBring your own AI |
| Comments with every post | YesUp to 100 per post, included | PartlySeparate scraper, billed per comment |
| Themes across many posts | Yes2 to 15 named themes per question | NoNone |
| Price | Starting at $49, everything included | From 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.
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.
In Claude or ChatGPT
Add buzzabout as a connector and ask in plain English. That's it.
- Start your free trial.
- In Claude or ChatGPT, add a custom connector with
https://mcp.buzzabout.ai/mcpand sign in. - Ask about Facebook.
In Claude Code or your own agent
Install the MCP server and let Claude Code build on it: digests, dashboards, alerts.
- Run
claude mcp add --transport http buzzabout https://mcp.buzzabout.ai/mcp. - Tell Claude Code what to build, for example a weekly digest of Facebook posts about your competitors.
- 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 Facebook say about
first-time home buyer mistakes?"1. In ChatGPT, add a custom connector (MCP server).
2. URL: https://mcp.buzzabout.ai/mcp
3. Sign in, then ask:
"What do people on Facebook say about
first-time home buyer mistakes?"claude mcp add --transport http buzzabout https://mcp.buzzabout.ai/mcp
# then, in Claude Code:
> Build a weekly digest of Facebook posts about
first-time home buyer mistakes, with the top hooks, questions
and sentiment, posted to our Slack webhook.{
"mcpServers": {
"buzzabout": {
"url": "https://mcp.buzzabout.ai/mcp"
}
}
}curl -X POST https://api.buzzabout.ai/v1/ask \
-H "x-api-key: $BUZZABOUT_API_KEY" \
-H "Content-Type: application/json" \
-d '{"message": "What do people on Facebook say about first-time home buyer mistakes?"}'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 freePro
$178/month
5,000 credits a month. Audience research. Up to 1,000 posts per research.
Try for freeBusiness
$450/month
20,000 credits a month. REST API. Unlimited listening agents.
Try for freeFree trial with 1,000 credits. A card is needed to sign up. See pricing.
Questions
What is the best Facebook MCP for research?
buzzabout. Connect it to Claude or ChatGPT and ask about any topic, public page, profile or group: every Facebook post comes back checked against your question, read and labeled, with real views on video, transcripts, comments and 17 analysis actions, 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.
What replaced CrowdTangle?
Meta shut CrowdTangle down in August 2024 and directs researchers to the Meta Content Library. The Graph API still covers only the Pages you manage. For brands, agencies and startups that follow public pages and groups, buzzabout collects their public posts by URL or keyword and hands them to Claude already analyzed, with transcripts on video. Try it free.
Can I pull posts from a public Facebook group?
Yes. Paste the group's URL into Claude and ask. The buzzabout research agent collects its feed, just like a public page or profile. Each post comes back with engagement and the full analysis, its comments are readable through the MCP, and pattern detection can name the 2 to 15 themes the group keeps coming back to.
Can I get Facebook comments through an API?
Yes. buzzabout collects up to 100 top-level comments per post 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.
Are Facebook view counts real?
On video posts, yes: buzzabout returns Facebook's own view count, flagged are_views_estimated: false. Other posts carry an estimate built from engagement, flagged true. You always know which number you have, so your reports hold up.
Why not just use a scraper or another data provider for Facebook?
A scraper hands you raw Facebook records and stops, and some data providers cannot even search Facebook by keyword; they need post or profile URLs first. Relevance filtering, transcription, on-screen text, 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.
How much does buzzabout cost for Facebook 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 Facebook 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.
Try it on your own topic
Free trial. Works in Claude and ChatGPT.
Free trial with 1,000 credits · MCP on every plan