MCP-native · not another chat app

The data layer that makes any AI assistant fluent in your business feeds.

FeedGPT connects to your social channels, cleans and structures the data, and hands it to Claude, ChatGPT, or your own agent over MCP — no proprietary chatbot to learn, no dashboard to babysit.

// works with Claude, ChatGPT, and any MCP-compatible client

Backed by:
NVIDIA Inception Program MemberINSEAD AI Venture Lab
01 · Raw payload
{ "message": "New service
  launch today",
  "created_time": null,
  "likes": "1,204" }
02 · FeedGPT heals it
content: "New service
  launch today"
likes: 1204
confidence 0.94 · logged
03 · MCP
MCP
tool calls
04 · Your analyst
Claude
ChatGPT
Your own agent
How it works

Three steps. No new interface to learn.

FeedGPT isn't a dashboard you check or a chatbot you talk to instead of the ones you already use. It's the plumbing between your feeds and the AI you already have open.

01

Point your feeds at a webhook

Every source gets its own endpoint. Send data straight from the platform, or automate it through Zapier, Make, Apify, or a custom script — anything that can POST JSON works.

02

FeedGPT cleans and structures it

Field mapping, deduplication, and schema healing turn inconsistent raw payloads into a standard shape — with a confidence score and audit entry for every decision.

03

Ask your AI about it

Connect the FeedGPT MCP server to Claude, ChatGPT, or your own agent. The intelligence is whichever model you're already using — FeedGPT just gives it something reliable to read.

Six real workflows

What agencies ask their AI — once their data is clean.

Copy any prompt, paste it into Claude, run it against Demo mode. No configuration.

Monday portfolio review

"Compare all my clients this month. Rank them, flag what changed direction, tell me what to act on today."

Replaces every dashboard login with one question.

Content diagnosis

"Group posts by theme. Show engagement and shares separately. Which theme is underrated?"

Finds the high-share content your likes-sorted dashboard buries.

Reports on demand

"Generate this month's client deck — KPIs, trends, top posts, recommendations. Real numbers only."

Same prompt monthly, same quality from every account manager.

Upsell detector

"Explain the engagement gap between these two clients. Draft the pitch to expand the weaker one's scope."

Your best client becomes the sales deck for the rest.

Audience research

"What earned disproportionate engagement relative to posting frequency? Show me what's undersupplied."

Evidence-based creative briefs instead of intuition.

The QA gate

audit trail
"Any malformed data, duplicates, or schema changes that could make a reported number wrong?"

Every answer backed by FeedGPT's audit trail. Show clients the log behind their report.

Run all six right now

Demo mode gives you a sample agency portfolio (three clients, six months of data) the moment you sign up. Free tier, no card.

Built for messy real-world data

Every field extraction has a paper trail.

Social platforms change their payload shapes without warning. FeedGPT is built to notice, adapt, and show its work — not to fail silently.

SchemaSense

Confidence-gated healing

When a payload doesn't match the expected shape, FeedGPT proposes a fix and only applies it once confidence clears your threshold. Below that, it's flagged for review — never guessed silently.

mappedFields: 6/7 · confidence: 0.94
actor: auto-heal · platform: facebook
Full audit log

Trace any number back to its source

Every ingestion, healing decision, and type mismatch is logged with a timestamp and confidence score — so "why does this say 42 likes" always has a real answer.

typeIssue:"not_a_number" rejected
fallback: honest null, not a guess

Roadmap: schema-healing inference moving to infrastructure we control (via the NVIDIA Inception Program), so payload diagnosis never has to leave our own environment. This is separate from the AI you connect over MCP to analyze your data — that's still your Claude or ChatGPT, on your terms.

Connect in seconds

Works with what you already automate with.

The webhook endpoint is a standard HTTP target. If your tool can send a POST request, it can feed FeedGPT.

Native webhooks
platform → source
Zapier
POST action
Make.com
HTTP module
Apify
actor output

Because we can't control what shape of payload an automation tool sends, schema healing isn't a nice-to-have here — it's what makes "connect anything" safe to promise.

For teams who get asked "prove it"

For agencies and regulated teams who get asked to prove their numbers.

Data you can defend

Agencies and regulated teams don't get to say "the dashboard looked right." FeedGPT keeps the evidence: what came in, what changed, and why.

Recognized by the NVIDIA Inception Program and INSEAD AI Venture Lab for the underlying data-infrastructure approach.

  • Every extraction logged with confidence + reasoning
  • Malformed input rejected, not silently ingested
  • Duplicate detection across every source
  • No data leaves your control to reach the AI — MCP connects your existing assistant directly
Pricing

Pay for data infrastructure. Bring your own AI.

No per-seat chatbot license — you already pay for Claude or ChatGPT. FeedGPT prices on sources and ingestion volume.

Free
$0/mo
Try it on one real source
  • 1 source
  • 1,000 events / month
  • 7-day audit log retention
  • Community support
Starter
$29/mo
For a single client or small team
  • 5 sources
  • 25,000 events / month
  • 30-day audit log retention
  • Email support
Most common
Growth
$199/mo
For agencies running multiple clients
  • 25 sources
  • 150,000 events / month
  • 90-day audit log retention
  • Auto-heal threshold tuning
  • Priority support
Enterprise
Custom
Government, regulated, or high-volume orgs
  • Unlimited sources
  • Custom event volume
  • Unlimited audit log retention
  • SSO + dedicated support
  • SLA on ingestion uptime
Talk to us

Events = webhook deliveries received, including from Zapier, Make, or Apify. Overages billed per 1,000 events; no source ever silently stops ingesting because of a cap.

Give your AI something real to read.

Connect a source, point Claude or ChatGPT at the MCP server, and ask your first question.