ai-first-scraper-mcp
llms.txt2 starsChanged 6 months agoMITView on GitHub
MCP (Model Context Protocol) server that exposes ad-free web scraping and search as three tools for Claude Desktop / Cursor / Cline / any MCP-compatible agent. After restart, three tools become available:
We split this llms.txt into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
After restart, three tools become available:
≈ “Common” is an estimate: at least 1 in 5 of the 3,225 llms.txt files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
# ai-first-scraper-mcp
> MCP (Model Context Protocol) server that exposes ad-free web scraping and search as three tools for Claude Desktop / Cursor / Cline / any MCP-compatible agent.
## Install for an AI agent (Claude Desktop / Cursor / Cline)
```json
{
"mcpServers": {
"ai-first-scraper": {
"command": "uvx",
"args": ["ai-first-scraper-mcp"]
}
}
}
```
After restart, three tools become available:
| Tool | Args | Returns |
|------|------|---------|
| `fetch_page` | `url: str, max_tokens?: int` | Clean Markdown body (HTML or PDF). |
| `fetch_pages_batch` | `urls: list[str] (≤25), max_tokens?: int` | Per-URL `{url, ok, data?, error?}` objects. |
| `search_web` | `q: str, k: int = 5, max_tokens?: int` | Top-k result pages already converted to Markdown. |
## Config (optional)
Point at your own backend with env vars:
- `SCRAPER_URL` (default `https://ai-first-scraper.onrender.com`)
- `SEARCH_URL` (default `https://ai-first-search.onrender.com`)
## Related
- https://github.com/yubinkim444/ai-first-scraper — backing scraper API.
- https://github.com/yubinkim444/ai-first-search — backing search API.
- https://github.com/yubinkim444/mcp-rec — record & replay this server's traffic for tests.
## About the author
Built by yubinkim444, who also makes Kay's Records, an app for iOS and Android:
https://kay-s-record.web.app/get.html
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.