---
title: "web-clipper"
description: "提取公开网页正文并保存为带来源的本地 Markdown 剪藏，可检索已收集资料。"
canonical: https://agentpluginsdirectory.com/plugins/web-clipper
last-updated: 2026-10-21
---

# web-clipper
提取公开网页正文并保存为带来源的本地 Markdown 剪藏，可检索已收集资料。
- Slug: web-clipper
- Publisher: XOPC
- Repository: https://github.com/xopcai/xopc-plugins
- Manifest: plugins/web-clipper/plugin.json
- Version: 1.0.0
- License: Apache-2.0
- Category (editorial): other
- Skills: 1 (web-clipper)
- MCP servers: 1 (web-clipper)
- Stars: 0
- Repository created: 2026-09-30
- Repository last pushed: 2026-10-19
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/web-clipper
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What web-clipper does, in the publisher's words

提取公开网页正文并保存为带来源的本地 Markdown 剪藏，可检索已收集资料。

在 XOPC 扩展市场安装，默认供所有 Agent 使用。无需云账号；在对话里提供资料、文件路径或公开链接即可使用。

Use article_read for readable text and clip_save only when the user asks to collect or save the article. clip_search searches this plugin's private local library.

- Ground the exact URL. Fetch public pages or pass HTML explicitly supplied by the user together with its source URL. Never send browser cookies, hidden credentials, or account pages to this tool.
- Inspect the returned title, text and truncation indicator. For blocked, login-only, paywalled or JavaScript-only pages, use the browser or request an export; do not claim extraction succeeded from a generic login page.
- When asked to save, use clip_save and return the actual Markdown path. Saving is idempotent by URL and does not overwrite an existing clip. Tell the user if an older clip already exists.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/xopcai/xopc-plugins/HEAD/plugins/web-clipper/README.md

## MCP servers

- web-clipper: transport: stdio; command: node ${PLUGIN_ROOT}/mcp/server.mjs

Read from the plugin's own mcp.json. Environment variable names only, never values.