Happy slice of mcp pizzaMCP.pizza

fitter

MCP.Pizza Chef: PxyUp

Fitter runs on your own computer and reads a page the way you describe it, handing back just the pieces you asked for instead of a wall of text. Your assistant writes the short recipe saying where to look, checks it, and runs it locally, so nothing passes through a third-party scraping service and there is no per-request bill. That recipe is a plain file, so tomorrow you can re-run the same collection without rebuilding it. Works with Claude Desktop, Claude Code, and other assistants.

Data
Web/Research

Use This MCP server To

Grab the top stories and their scores from a news site Pull today's prices from a page I check every morning Collect a list of items spread across several pages Re-run yesterday's collection without setting it up again Read a page that only loads properly in a real browser Build myself a short morning briefing from a few sites

README

Fitter — web data for AI agents

MCP Toplist

Release License: MIT Go Reference Sponsor

Fitter turns any website or API into structured JSON — declaratively. One JSON/YAML config describes where the data lives (HTTP request, headless browser, file, static value) and what to extract (JSON paths, CSS selectors, XPath). No code, no brittle scraping scripts.

🚀 Try it in your browser — the real engine compiled to WebAssembly: live examples, a visual config builder, no install.

Because configs are plain data, LLMs can author them. The built-in MCP server lets Claude Code, Claude Desktop, or any MCP client write and run scraping pipelines on your machine, on demand:

"Get the top 5 HackerNews stories with titles and scores" → the model authors a fitter config, validates it, runs it locally, and gets clean JSON back.

One engine, five ways to use it:
🤖 Fitter MCP MCP server exposing fitter to Claude Code, Claude Desktop and any MCP client
🧠 Fitter Agent AI-powered CLI: natural language → config → executed result
🖥 Fitter CLI run configs locally for test/debug/home usage
📦 Fitter Lib embed the engine in your own Go program
⚙️ Fitter long-running service mode with scheduling & notifications

Why fitter for AI agents?

  • Declarative & auditable — the agent produces a config you can read, save and re-run, not throwaway code
  • Local-first — all fetching happens on your machine; no third-party scraping API, no keys, no per-request billing
  • Batteries included — HTTP client, headless browser (Playwright/Chromium/Docker), JSON/HTML/XML/XPath/PDF parsing, pagination, cached references, host rate-limits — in a single static binary
  • Reusable — what the agent authored today becomes tomorrow's cron job or service config

fitter demo — declarative config to structured JSON

How to use Fitter_MCP

Fitter MCP is a Model Context Protocol server (stdio transport) which lets any MCP client — Claude Code, Claude Desktop, IDE assistants, custom agents — run Fitter configs and get structured JSON back.

fitter FAQ

Which apps does this work in?
Claude Desktop, Claude Code, and any other assistant that speaks MCP. A ready-made bundle installs it into Claude Desktop when you open the file.
Do I have to pay per page or sign up for a scraping service?
No. All the fetching happens on your own machine, so there is no account, no billing, and no per-request charge.
Can I use this to check a price or a listing every day?
Yes — the recipe your assistant writes is a saved file you can re-run whenever you like, or put on a schedule later.
How hard is setup?
Download the file for your computer and either open it, on Claude Desktop, or paste one short line to register it. No coding involved.
Does it handle pages that need a real browser?
Yes. It can drive a headless browser for pages that will not load otherwise, alongside plain page fetching and PDF reading.
Can my whole team share one?
Yes. It can also run as a shared server behind a password, which suits a team or a container setup.