Google PageRank for AI agents. 25,000+ tools indexed.

lsbot MCP Server

ruilisi/lsbot

Score: 56.0 Rank #8847 MCP Server
[![AgentRank](https://agentrank-ai.com/api/v1/badge/ruilisi--lsbot)](https://agentrank-ai.com/tool/ruilisi--lsbot/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
Are you the maintainer of ruilisi/lsbot? Claim this listing →

Lean & Secure Bot

Add AgentRank to Claude Code Discover and compare tools like ruilisi/lsbot — your AI finds the right one automatically
Get API Access →
claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

ruilisi/lsbot is a Go tool. Lean & Secure Bot Topics: bot, mcp-server, openclaw, secure.

Ranked #8847 out of 24846 indexed tools.

Ecosystem

Go No license
botmcp-serveropenclawsecure

Score Breakdown

StarsFreshnessIssue HealthContributorsDependents
Stars 15% 408

408 stars → growing community

Freshness 25% 6mo ago

Last commit 6mo ago → stale

Issue Health 25% 85%

17/20 issues closed → responsive maintainer

Contributors 10% 2

2 contributors → solo project

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A
PyPI Downloads N/A
Forks 54
Description Brief
License None

Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →

How to Improve

Description low impact

Expand your description to 150+ characters for better discoverability

License low impact

Add an MIT or Apache-2.0 license to signal trust and enable adoption

Freshness high impact

Last commit was 198 days ago — a recent commit would boost your freshness score

Badge all embed codes →

AgentRank score for ruilisi/lsbot
[![AgentRank](https://agentrank-ai.com/api/v1/badge/ruilisi--lsbot)](https://agentrank-ai.com/tool/ruilisi--lsbot/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
<a href="https://agentrank-ai.com/tool/ruilisi--lsbot/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/ruilisi--lsbot" alt="AgentRank"></a>

Embed Widget docs →

Embed a rich score widget on your site or blog.

<script src="https://agentrank-ai.com/embed.js" data-tool="ruilisi/lsbot"></script>

Matched Queries

topic:mcp-server

From the README

[English](./README_EN.md) | 中文

<div align="center">
  
</div>

---

# lsbot — Lean & Secure Bot

> **不需要信任的地方,就不应该建立信任依赖。**

> 📖 **文档:[lsbot.org/docs](https://lsbot.org/docs)** | 国内镜像:[lsbot.net/docs](https://lsbot.net/docs)

---

## Bot Needs to be Secured

当你运行一个 AI Bot,你实际上把机器的钥匙交了出去:文件、终端、数据库、浏览器会话、凭证。Bot 读取你的代码、笔记、私人文档,并以你的名义执行命令。

问题不是 Bot 是否有用。**问题是:还有谁能看到它看到的东西?**

你每天操作电脑,层层加密加锁——密码管理器、磁盘加密、双重验证。但当你打开一个 AI Bot,这一切防线往往荡然无存。你的每一条消息、每一个工具调用结果,都在你不知情的情况下流经某台你不控制的服务器。

这不是理论风险。这是今天几乎所有 AI Bot 工具的默认配置。

---

## Why OpenClaw is Not Secured

OpenClaw(以及大多数同类工具)以便利性和功能广度为设计目标,安全性是事后考虑,而非核心设计原则。

| 问题 | 意味着什么 |
|---|---|
| 消息通过开发者的云服务路由 | 服务商可以读取每一条消息 |
| 没有端到端加密 | 任何中继节点都可以审查内容 |
| npm 依赖链 | 500+ 第三方包,任何一个都可能被攻击 |
| Node.js 运行时 | 动态执行环境,攻击面庞大 |
| 没有本地数据保证 | 对话历史、上下文、记忆——存储位置不明 |

OpenClaw 在功能和集成方面做得出色。但它的架构假设你信任中继基础设施。对于个人电脑、企业环境,或任何数据敏感的场合,这个假设不成立。

当你把终端和文件的访问权限交给 AI Bot,传输层必须被当作敌对环境对待。OpenClaw 没有做到这一点。

---

## Why lsbot

`lsbot` 是 **Lean Secure Bot** 的缩写。名字也呼应了 `ls`——Unix 最基础的命令,
Read full README on GitHub →

Get the weekly AgentRank digest

Top movers, new tools, ecosystem insights — straight to your inbox.