What is mcp AGENTS.md?

Instructions for the FourA MCP server, which fetches public web pages, APIs, JavaScript-rendered sites, and pages protected by anti-bot checks. It provides four read-only fetching methods, including direct requests, proxies, and browser sessions.

Use it to retrieve public web content with automatic method selection or with explicit control over HTTP, proxy, and browser requests.

It explains which fetching method to try when a normal web request is incomplete, blocked, or cannot run JavaScript.

How fouradata/mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to fouradata/mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/fouradata/mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/fouradata/mcp

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/fouradata/mcp/agents-md/github.svg)](https://agentmods.dev/instructions/fouradata/mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/fouradata/mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/fouradata/mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/fouradata/mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/fouradata/mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 809 This file is loaded in full into every session.

When invoked 809 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00809	$0.00809
Opus 5.5	$0.00324	$0.00324
Sonnet 5.5	$0.00162	$0.00162
Haiku 4.5	$0.00081	$0.00081

Measured 1mo ago against content hash 30434bcb033a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Agent-facing reference for the FourA MCP server (@fouradata/mcp). If you are an AI agent deciding whether and how to use this server, read this.

What this server does

Fetches arbitrary public web pages for you: static pages, JSON APIs, JavaScript-rendered SPAs, and anti-bot-protected targets. It wraps the FourA web scraping API. All tools are read-only (readOnlyHint: true) and reach the open web (openWorldHint: true).

Tools (four)

foura_auto - the default. Give it a url; it returns the content and picks the fetch method for you. Use this first unless you need explicit control. Optional validate.data.accept lets it tell a real page from a challenge page.
foura_single - one fast HTTP request. Static pages and JSON APIs. A full browser header set is sent by default (unblocker); set browser, os, or version when a target refuses the default Chrome.
foura_proxy - the same request through a rotating proxy pool with retry. Use when a direct request is blocked; difficult protected targets may need maxTries: 25-30. The inner request takes the same browser-profile fields. exitClass: "premium" allows escalation to a premium exit for a target the standard pool cannot reach, and the response says which class served. A failed rotation returns attemptReport, which separates blocked exits from dead ones from pages your own validate rule rejected.
foura_browser - a real browser session; JavaScript runs and the DOM finishes rendering. Use for SPAs and lazy-loaded content.

The primitives compose: foura_proxy returns a base36 proxy ID; pass it into foura_single.proxy or foura_browser.proxy to reuse the same exit.

Prompts (six)

smart_fetch, scrape_product_page, extract_article, monitor_pricing, check_endpoint_health, bulk_fetch_urls. Each expands into a templated task that orchestrates the tools for you.

Errors

Every error carries a structuredContent envelope with {service, code, error} and, where relevant, status / retryAfter. Read code for retry logic: rate_limited, at_capacity, service_unavailable, upstream_error are retry-safe (respect retryAfter); auth_failed, bad_request, not_found, ssrf_blocked are not. A code starting with plan_limit_ is the caller's own FourA plan refusing the call rather than the target: the same work through another tool is refused as well, so wait out retryAfter or change the plan. Full list: https://foura.ai/docs/mcp/errors.

Read the full file on GitHub · 66 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago Changed · +11 lines · +161 tokens per session 30434bcb033a
2mo ago First seen · 55 lines · 648 tokens per session scan A 9c88d3698144

Subscribe to this mod's changes

mcp AGENTS.md is an instructions file published in the GitHub repository fouradata/mcp (7 stars, last pushed 2d ago), licensed MIT. It adds 809 tokens to every session, about $0.0032 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Browser automation TypeScript ai-agents claude mcp model-context-protocol web-scraping

mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp AGENTS.mdfouradata/mcp	Instructions file	7	2d ago	MIT	A	809	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp: Instructions file for Codex