agentmods.dev

webclaw

webclaw is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from 0xMassi/webclaw. Its token cost is not measured, scanned A, original, AGPL-3.0.

A local tool for web search, page scraping, website crawling, structured data extraction, and research. It runs as an MCP package, a service format that lets an AI agent use external tools.

In plain words
What is it for?
Use it to find web sources, crawl pages, extract structured information, and support research tasks.
Why use it?
It removes the need to gather web information manually or turn unstructured pages into usable data by hand.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it.

not rated 2.4krepo +11 today A scan tokens not measured AGPL-3.0

Good fit Use it to find web sources, crawl pages, extract structured information, and support research tasks.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/0xmassi/webclaw/create-webclaw-webclaw
View source ↗ 0xMassi/webclaw webclaw.io
About the project

webclaw is a web-content extraction tool that turns webpages into clean Markdown, JSON, and context suitable for language models. It is for AI agents and retrieval-augmented applications that need usable content from websites, and can be used through a CLI, REST API, SDKs, or MCP server. The catalogue includes instructions and an MCP integration for connecting compatible agents to it.

0xMassi/webclaw · 2,436 stars · on GitHub · webclaw.io

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.

Clone the repo
git clone --depth 1 https://github.com/0xMassi/webclaw

Made for: Claude Code, Codex, Cursor, Gemini CLI, 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.

agentmods badge for webclaw

README.md
[![agentmods](https://agentmods.dev/badge/mcp/0xmassi/webclaw/create-webclaw-webclaw/github.svg)](https://agentmods.dev/mcp/0xmassi/webclaw/create-webclaw-webclaw)
Your own site
<a href="https://agentmods.dev/mcp/0xmassi/webclaw/create-webclaw-webclaw"><img src="https://agentmods.dev/badge/mcp/0xmassi/webclaw/create-webclaw-webclaw/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.

agentmods 80×15 button for webclaw

Your own site · 80×15
<a href="https://agentmods.dev/mcp/0xmassi/webclaw/create-webclaw-webclaw"><img src="https://agentmods.dev/badge/mcp/0xmassi/webclaw/create-webclaw-webclaw.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown No closer match found in the catalogue.
Security

Grade A, and why

webclaw 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 yesterday.

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.

packages/create-webclaw/server.json · 12 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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.

  1. yesterday First seen · 12 lines scan A 369a3c1e90c9

Subscribe to this mod's changes

webclaw is an MCP server published in the GitHub repository 0xMassi/webclaw (2,436 stars, last pushed today), licensed AGPL-3.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 2026-11-08.

Browser automationLLMResearchRustai-agentsclimarkdownmcp
Related

webclaw compared with mcp servers from other repositories

webclaw next to 6 mcp servers from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
webclaw0xMassi/webclawMCP server2.4ktodayAGPL-3.0A—Claude Code, Codex, Cursor, Gemini CLI, OpenCode
llmwikiatomicstrata/llm-wiki-compilerMCP server2.2k10d agoMITA—Claude Code, Codex, Cursor, Gemini CLI, OpenCode
amenboRererr/amenboMCP server0todayMITA—Claude Code, Codex, Cursor, Gemini CLI, OpenCode
simplicio-runtimewesleysimplicio/simplicioMCP server281mo agononeA—Claude Code
mdbGiantRavens/mdbrowseMCP server03mo agoMITA—Claude Code, Codex, Cursor, Gemini CLI, OpenCode
pdftomarkdown-fyiHEMANT16/pdftomarkdownMCP server12mo agononeA—Claude Code, Codex, Cursor, Gemini CLI, OpenCode
docs-langchainlangchain-ai/langchainMCP server149ktodayMITA—Claude Code, Codex, Cursor, Gemini CLI, OpenCode