A browser-automation service that can navigate pages, interact with forms, collect page data, and inspect a live browser's developer information. It also exposes network traffic, console errors, storage, accessibility results, and code coverage.

Use it for web scraping, form workflows, live page debugging, network and console inspection, accessibility audits, performance checks, and coverage checks.

It removes the need to perform repetitive browser checks manually or guess why a page is failing. The inspection tools show both what the page displays and what happens behind it.

acrawl-mcp — Skill for Claude Code and Codex by Mingye-Lu

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add Mingye-Lu/AgenticCrawler --skill acrawl-mcp

Clone the repo

git clone --depth 1 https://github.com/Mingye-Lu/AgenticCrawler

Made for: Claude Code, Codex.

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/skills/mingye-lu/agenticcrawler/acrawl-mcp/github.svg)](https://agentmods.dev/skills/mingye-lu/agenticcrawler/acrawl-mcp)

Your own site

<a href="https://agentmods.dev/skills/mingye-lu/agenticcrawler/acrawl-mcp"><img src="https://agentmods.dev/badge/skills/mingye-lu/agenticcrawler/acrawl-mcp/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/skills/mingye-lu/agenticcrawler/acrawl-mcp"><img src="https://agentmods.dev/badge/skills/mingye-lu/agenticcrawler/acrawl-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 200 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,520 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00200	$0.04520
Opus 5.5	$0.00080	$0.01808
Sonnet 5.5	$0.00040	$0.00904
Haiku 4.5	$0.00020	$0.00452

Measured 9d ago against content hash 2ec2aa540a22, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

acrawl-mcp 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 9d 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.

skills/acrawl-mcp/SKILL.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

acrawl MCP

acrawl exposes 40 MCP tools: 32 browser/DevTools tools, 7 script tools, and 1 autonomous agent (run_goal). All 40 share one persistent browser session across calls — except run_goal, which builds its own isolated agent and browser.

What makes acrawl different from other browser MCPs is the observability half: you can read network traffic, console logs, WebSocket frames, cookies, storage, coverage, and axe-core audits from a live page. Reach for those instead of guessing why a page misbehaves.

Tool names below are bare (navigate). Your client may namespace them (acrawl_navigate, mcp__acrawl__navigate) — use whatever prefix your tool list shows.

1. Pick an execution mode first

Three ways to get work done. Choosing wrong is the most expensive mistake available, because it either burns tokens on a loop that should have been a script, or spends a script debugging cycle on a one-off click.

Mode	Use when	Cost
Manual tool calls	Exploring an unfamiliar page; <10 actions; you need to see each result to decide the next step	1 LLM round-trip per action
Batched tool calls	A short, predictable sequence (2–5 calls) whose inputs don't depend on each other's output	1 LLM round-trip for the whole sequence
`run_script`	Same operation over 3+ pages/items, and the page structure is already known	Zero LLM round-trips during execution
`run_goal`	Whole task is delegable in one sentence and you don't need intermediate control	1 call; agent burns its own tokens internally

The practical pattern: explore manually until the shape is known, batch the short predictable sequences, then script the repetition. Do one page by hand, confirm your selectors, then turn the loop into a script. A 50-page crawl becomes one tool call instead of 150.

Reach for run_goal when the target is genuinely unknown and adaptive ("find the pricing page and extract every tier"). It needs ~/.acrawl/credentials.json configured; the other 38 tools do not. If credentials are missing, run_goal fails and the correct move is manual tools or a script, not repeated retries. See references/setup.md.

Read the full file on GitHub · 210 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

9d ago Changed 2ec2aa540a22
20d ago Changed · -10 lines 451f9c43f154
25d ago Changed ce9febbb5280
1mo ago Changed · +25 lines b8615e053722
1mo ago First seen · 195 lines · 200 tokens per session scan A 47eed4d97836

Subscribe to this mod's changes

acrawl-mcp is a skill published in the GitHub repository Mingye-Lu/AgenticCrawler (15 stars, last pushed yesterday), licensed MIT. It adds 200 tokens to every session and 4,520 once invoked, about $0.0008 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 2026-09-13.

Autonomous Agents Browser automation Debugging ai-agent browser-automation cli cloakbrowser developer-tools

acrawl-mcp next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
acrawl-mcpMingye-Lu/AgenticCrawler	Skill	15	yesterday	MIT	A	200	Claude Code, Codex
opencli-autofixjackwener/OpenCLI	Skill	31k	yesterday	Apache-2.0	A	61	Claude Code
surfnicobailon/surf-cli	Skill	684	yesterday	MIT	A	53	Claude Code, Codex
playwright-cliadbertram/cli-tools	Skill	6	today	MIT	A	153	Claude Code, Codex
debug-failed-actionfrane/vibesurfer	Skill	17	1mo ago	Apache-2.0	A	54	Claude Code
opencli-browserjackwener/OpenCLI	Skill	31k	yesterday	Apache-2.0	A	43	Claude Code
opencli-adapter-authorjackwener/OpenCLI	Skill	31k	yesterday	Apache-2.0	A	38	Claude Code