Apify Insights MCP
ShippedOpen-source MCP server that lets Apify creators ask Claude, Codex or Cursor about their own account: what earns, what broke and what to fix.
Creator, sole engineer · Open source · 2026
- Tools
- 12
- AI apps supported
- 6+
- Tests
- 200+
- Releases in 3 days
- 7
Problem
Account answers were scattered across Apify's console, and AI assistants couldn't see them.
What I built
A read-only MCP server that plugs into Claude, Codex, Cursor and other AI apps.
Result
Ask "what broke last night?" and get the answer from live data.
What it does
01
Morning brief
One question for earnings, failures and what needs attention.
02
Why runs failed
Failed runs with log lines and the build behind them.
03
Pricing help
Profit per scraper and the break-even price.
04
Growth and rank
User drop-off, rising and fading scrapers, and store rank.
05
No token copying
A short-lived login token, passed only when needed.
06
Built for AI assistants
Read-only tools, and "not available" instead of zero.
Tech Stack
All projects- TypeScript
- MCP SDK
- Node.js
- esbuild
- Vitest
Read the full write-up1 min read
The problem
The answers I needed every morning were spread across Apify's console: what earned, which runs failed and why, where users dropped off, how I ranked in the store. Getting them meant a lot of clicking, and an AI assistant couldn't help because most of that data has no public API.
Highlights
- Ask in plain words, like "what broke last night?", and get answers from live account data
- One command adds it to Claude Code, Codex, Gemini CLI, Cursor and more
- It can only read. A fixed list of allowed requests means it can't change or delete anything
- 200+ automated tests and 7 releases in 3 days
- The same pattern works for a client: give your team's AI assistant safe, read-only access to data it can't reach today
What I built
- Morning brief
- Ask "how am I doing?" and get earnings, failed runs and the scrapers that need attention in one answer.
- Why runs failed
- Failed runs per day, the last lines of each log, and the build that was live when the failures started.
- Pricing help
- Profit per scraper and the break-even price, so you can see which ones lose money and what price fixes that.
- Growth and rank
- Where users drop off, which scrapers are rising or fading, and where you rank in the store.
- No token copying
- A small browser bridge hands over a short-lived login token only when the server asks for one, saved in a file only you can read.
- Built for AI assistants
- Every tool is marked read-only, a glossary explains each metric, and missing data shows as "not available" instead of zero, so the assistant doesn't guess.
Related Projects
Interested in working together?