legado-unofficial MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@legado-unofficial MCP Servertest this CSS rule on the page I just fetched"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
LegadoTeam 非官方二改版(legado-unofficial)
⚠️ 重要声明:这不是官方版本,是个人二改版
本仓库是个人对 LegadoTeam(阅读) 的二次修改版(二改版),仅供自用构建与学习交流,与 Legado 官方团队无任何关系,不是官方发布。
请勿将本版的问题、构建产物反馈给官方(官方仓库 / 官方群组)。使用本版产生的一切问题由使用者自行承担。
需要原版与原版支持,请前往官方仓库:LegadoTeam/legado。
English: This is an unofficial, personally modified build ("二改版") of LegadoTeam. It is NOT affiliated with, endorsed by, or supported by the Legado team. Please do not report issues about this build to the official repository.
这是什么
基于原版 LegadoTeam 源码(提交 62003ce,2026-09-13)的二次修改版,主要增强 MCP 书源开发能力(用 AI 辅助编写、调试书源),并更换了应用包名。构建产物由 GitHub Actions 自动生成,仅供个人测试使用。
Related MCP server: Chrome DevTools MCP
本版改动
包名变更(改回了官方版,我懒得共存,也没签名校验,用mt随便改)
应用包名:
com.legado.app→io.legado.app(release:io.legado.app.release,debug:io.legado.app.debug)⚠️ 包名与官方版不同,无法覆盖安装官方版,需先卸载官方版再安装本版
MCP 书源开发增强
书源变更历史与回滚:新增
list_history/restore_source工具,每次保存/删除书源自动留存快照(数据库 v112 新增book_source_history表,每源保留最近 20 条)HTTP 日志增强:日志容量可调(1–500 条,默认 50,持久化保存);
get_http_logs支持sinceId增量轮询;新增set_http_log_capacity工具,立即裁剪并持久化调试日志增强:
debug_source逐行实时推送(缓冲通道,不再丢中间行),并在返回结果中附加结构化"环节链"摘要(搜索 / 详情 / 目录 / 正文 / 发现页各环节执行状态、入口参数与错误信息)网页抓取工具:
fetch_page(由 App 侧发起请求,自动检测编码,返回状态码/响应头/正文,超长正文自动分页)+fetch_more(按页取回,token 有效期 10 分钟)规则验证工具:
test_rule用一条 Legado 规则(CSS / XPath / JSONPath / 正则)快速解析给定 HTML/文本,保存书源前先验证规则是否命中
构建
由 GitHub Actions 自动构建(配置见
.github/workflows/build.yml):推送到master分支自动触发,也可在 Actions 页面手动触发(workflow_dispatch)产物:每次构建自动发布到 Releases(tag 形如
v3.270922,版本号从3.270922起自动递增),APK 同时上传 Actions Artifacts 备份签名:CI 中临时生成的 debug 签名,仅供测试安装,不适合正式分发或上架
许可
本项目基于 LegadoTeam(GPL-3.0)修改,遵循 GPL-3.0 开源许可(见 LICENSE)。
Related MCP Connectors
Live browser debugging for AI assistants — DOM, console, network via MCP.
Build, validate, deploy — HTTP APIs, cron jobs, webhooks and MCP tools — from your AI client.
One searchable history across every AI coding tool, with secret scanning and a shared task board.
Deploy your project to a live HTTPS URL from your AI tool; read logs, set variables, resize apps.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceProvides code manipulation, execution, and version control capabilities. It allows AI assistants to read, write, and execute code while maintaining a history of changes.9MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI coding assistants to control and inspect a live Chrome browser through Chrome DevTools. Provides browser automation, performance analysis, debugging capabilities, and network request monitoring.3,202,397 npm52,668Apache 2.0
- AlicenseAqualityAmaintenanceEnables AI coding assistants to debug and analyze JavaScript code in web pages through breakpoint debugging, function hooking, network analysis, and runtime inspection of scripts including minified code.24990 npm2,825Apache 2.0
- AlicenseNot gradedqualityDmaintenanceProvides tools for AI-driven development workflows including file system operations, code analysis, code execution, web fetching, and search.Apache 2.0