原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚 登录

BotArmor: LLM red teaming for chatbots

作者:sidorenkav-collab版本 0.1.2i★ 0i电脑或云端官方网站 ↗
注册名称io.github.sidorenkav-collab/botarmor

安装方法

能做什么

LLM red teaming and prompt injection testing for chatbots and AI agents: A-F grade, prompt fixes.

作者提供的原文

  • 连接方式 电脑或云端
  • 账号或密钥 云端:连接时登录该服务(OAuth) · 本地:需要 BOTARMOR_API_KEY
  • 分类 搜索与 AI 记忆

可搭配使用

教 AI 做这类工作的 Skill,可与本项一起使用

timesfm

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

作者:google-research★ 35,6421 个 skill

Skill · 操作手册

Shadowbroker

Open-source intelligence for the global theater. Track everything from the corporate/private jets of the wealthy, and spy satellites, to seismic events in one unified interface. Hook an AI agent up to have it parse through data and find previously unseen correlations. The knowledge is available to…

作者:BigBodyCobain★ 11,6081 个 skill

Skill · 操作手册

google-maps-scraper

scrape data from Google Maps. Extracts data such as the name, address, phone number, website URL, rating, reviews number, latitude and longitude, reviews,email and more for each place

作者:gosom★ 8,2561 个 skill

Skill · 操作手册

为什么排在这里

列表按使用分(满分 100)排序,由以下部分组成

热度0/80GitHub 星标或每周下载量:较大的计 60,较小的计 20
新鲜度12/1230 天内有发布或代码更新得满分
仍在响应8/8上次检查时云端端点有响应
使用分20/100

质量: 基础检查通过 5/5 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)

安装

选择你使用的 AI 应用,然后复制设置。

用一句话让 AI 帮你安装

请帮我安装 BotArmor: LLM red teaming for chatbots。按照 https://mcp.popnx.com/i/sidorenkav-collab-botarmor.md 操作,先把命令给我看,等我同意后再运行。

粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文

通过 5/5 项检查 · 你的提问会经过开发者的服务器(app.botarmor.eu) · ✓ 命令已检查 2026年11月20日

第一步:你用哪个 AI?

选择你用的应用,步骤会显示在下方。

可连接 Claude · 约 2 分钟

不需要密钥,不用安装程序 · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个 · Team/Enterprise 方案由所有者(Owner)添加

  1. 打开 Claude 的 Connectors 页面

    CustomizeConnectors

    CustomizeConnectors1Add2https://…3Add4
  2. 点击“Add” → “Custom” → “Web”,填写这 2 项

    把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue

    Name · 名称BotArmor: LLM red teaming for chatbots
    Remote MCP server URL · 地址https://app.botarmor.eu/mcp

    在 Claude 检测到的登录设置页点击 Continue · Authentication 按作者说明选择(Sign in now、Sign in when needed 或 No sign in),然后点击 Add

  3. 在聊天中开启

    +ConnectorsBotArmor: LLM red teaming for chatbots

  4. 试一试

    用 BotArmor: LLM red teaming for chatbots 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Claude 说正在使用 BotArmor: LLM red teaming for chatbots,或回答中出现 BotArmor: LLM red teaming for chatbots 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同

能否连接 ChatGPT 取决于方案

完整 MCP:网页版 ChatGPT Business、Enterprise 或 Edu · Pro:以读取/获取权限连接,修改数据的工具可能用不了 · Plus:官方文档尚未确认,如果在插件页看到添加自定义 MCP 的选项可以试试 · 仅限网页

  1. 在网页版 ChatGPT 打开添加 MCP 的页面

    Plugins+Add custom MCP server

    ChatGPTPlugins1+2https://…3Create4
  2. 填写名称和地址

    输入名称,在 Connection 下粘贴地址,勾选风险提示,然后点击 Create as a plugin

    Name · 名称BotArmor: LLM red teaming for chatbots
    Connection · 地址https://app.botarmor.eu/mcp
  3. 在聊天中选择 BotArmor: LLM red teaming for chatbots

    开启新聊天,输入前先从插件列表中选择 BotArmor: LLM red teaming for chatbots

  4. 试一试

    用 BotArmor: LLM red teaming for chatbots 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 ChatGPT 说正在使用 BotArmor: LLM red teaming for chatbots,或回答中出现 BotArmor: LLM red teaming for chatbots 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 OpenAI 帮助页面核实 · 你的界面可能因版本略有不同

可连接 Claude Code · 约 2 分钟

不需要密钥,不用安装程序

  1. 打开终端

    Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell

  2. 粘贴这条命令并按 Enter

    claude mcp add --transport http --scope user botarmor https://app.botarmor.eu/mcp
  3. 在 Claude Code 中输入 /mcp

    应能看到 BotArmor: LLM red teaming for chatbots 在列表中并显示已连接

  4. 试一试

    用 BotArmor: LLM red teaming for chatbots 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Claude Code 说正在使用 BotArmor: LLM red teaming for chatbots,或回答中出现 BotArmor: LLM red teaming for chatbots 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同

可连接 Cursor · 约 2 分钟

不需要密钥,不用安装程序

  1. 点击这个按钮打开 Cursor

    在 Cursor 中打开

    Cursor 会请你确认安装,点击 Install

  2. 在 Cursor 中以 Agent 模式打开 AI 聊天

  3. 试一试

    用 BotArmor: LLM red teaming for chatbots 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Cursor 说正在使用 BotArmor: LLM red teaming for chatbots,或回答中出现 BotArmor: LLM red teaming for chatbots 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同

可连接 VS Code · 约 2 分钟

不需要密钥,不用安装程序

  1. 点击这个按钮打开 VS Code

    在 VS Code 中打开

    VS Code 会请你确认安装,点击 Install

  2. 在 VS Code 中以 Agent 模式打开 AI 聊天

  3. 试一试

    用 BotArmor: LLM red teaming for chatbots 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 VS Code 说正在使用 BotArmor: LLM red teaming for chatbots,或回答中出现 BotArmor: LLM red teaming for chatbots 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同

其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看

查看所有支持 MCP 的应用 →

通过网页连接的应用使用的地址

地址https://app.botarmor.eu/mcp

JSON 设置在下方“开发者专用”中

卡住了?问问正在用 BotArmor: LLM red teaming for chatbots 的人💬 讨论 →
开发者专用:终端命令和 JSON 设置

通过网页连接

Claude Code

claude mcp add --transport http --scope user botarmor https://app.botarmor.eu/mcp

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "botarmor": {
      "url": "https://app.botarmor.eu/mcp"
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "botarmor": {
      "type": "http",
      "url": "https://app.botarmor.eu/mcp"
    }
  }
}

安装在电脑上

Claude Code

claude mcp add --scope user botarmor --env BOTARMOR_API_KEY=your-value -- npx -y @botarmor/mcp

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "botarmor": {
      "command": "npx",
      "args": [
        "-y",
        "@botarmor/mcp"
      ],
      "env": {
        "BOTARMOR_API_KEY": "your-value"
      }
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "botarmor": {
      "command": "npx",
      "args": [
        "-y",
        "@botarmor/mcp"
      ],
      "env": {
        "BOTARMOR_API_KEY": "your-value"
      }
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "botarmor": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@botarmor/mcp"
      ],
      "env": {
        "BOTARMOR_API_KEY": "your-value"
      }
    }
  }
}

需要你填写的值

  • BOTARMOR_API_KEY 机密 必填 env
    BotArmor API 密钥(ba_live_...),来自客户区的 API 标签页。
    查看英文原文BotArmor API key (ba_live_...), from the client area, tab API

说明为自动翻译,变量名保持原样;不确定时请查看原文。

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。

一览

每周下载量i
23/周
连接方式
电脑或云端
传输方式
stdio, streamable-http
最新版本i
0.1.2
发布到注册中心i
2026年11月20日
代码最后更新i
2026年11月20日
最近检查
2026年11月20日
作者
sidorenkav-collab
软件包
npm: @botarmor/mcp
注册状态
活跃

哪些应用可以使用它

依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。

通过互联网连接,适用于

ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast

在你的电脑上运行,适用于

ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast

全部应用及其优缺点 →

它能做什么

服务器要求先登录,才会列出它的工具。

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月20日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 sidorenkav-collab 验证,该账户拥有此仓库

  • ✓ 通过

    仍在维护

    代码最后更新于今天

  • ✓ 通过

    有许可证

    使用 MIT

  • ✓ 通过

    端点有响应

    在 756 毫秒内响应(HTTP 401)

  • ✓ 通过

    使用 OAuth 登录

    声明支持 OAuth 登录,你的 AI 应用可以带你去登录

  • … 尚未检查

    工具描述中没有隐藏指令

    尚未检查;我们会在检查端点时读取工具列表

已公开的漏洞(OSV.dev)

尚未检查

我们检查什么 → · JSON

作者:申请重新检查或报告信息错误
给作者:在 README 中加徽章

如果你是作者,可把这段代码贴到 README。徽章会链接回本页。

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/sidorenkav-collab-botarmor.svg)](https://mcp.popnx.com/en/servers/sidorenkav-collab-botarmor)

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

登录后发帖

用户评价

还没有评价

登录后写评价

与“搜索与 AI 记忆”中的其他服务器比较i

  • 星标数多于此分类中其他 6470 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 6470 个服务器的 99% 更新
  • 基础检查结果等于或优于此分类中其他 6470 个服务器的 99%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

BotArmor: LLM red teaming for chatbots 安全吗?

它在 5 项适用的基础检查中通过了 5 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

你需要填写:BOTARMOR_API_KEY

它在我的电脑上运行还是在云端?

两种方式都可以:安装在你的电脑上,或者连接云端版本。

它还在维护吗?

GitHub 仓库最后更新于今天,最新版本(0.1.2)于今天进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,因此也能用于接受远程 MCP 的应用,例如网页版 ChatGPT(Business 及以上为完整 MCP;Pro 为只读)。

有什么可以替代它?

同一分类中有:OpenSEO, Exa, Microsoft Learn MCP, Docs, COTAL actions (cotal.ai)

功能相近的其他选择

同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。

如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

OpenSEO

Keyword research, site audits, rank tracking and AI visibility for your AI agent.

作者:every-app广泛使用★ 2.8万6天前更新

在云端运行✓ everyapp.com

Exa

Official Exa MCP for web search, content fetching, and multi-step research.

作者:exa-labs广泛使用★ 5245今天更新

在云端运行✓ 服务方 · exa.aiPopNx 团队已实际试用

Microsoft Learn MCP

Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.

作者:MicrosoftDocs广泛使用★ 200012个月前更新

在云端运行✓ 服务方 · microsoft.comPopNx 团队已实际试用

Docs

Search and read Empryo's documentation. Read-only, no auth, no local access.

作者:proxysoul正在增长★ 16282个月前更新

在云端运行✓ empryo.com
与相似项目对比
本项
BotArmor: LLM red teaming for chatbots
OpenSEOExaMicrosoft Learn MCPDocsCOTAL actions (cotal.ai)
运行位置云端或安装在电脑上都可以在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装
需要密钥是否否否否否
可在 Claude 中按 + 添加否是是是否否
基础检查5/55/52/44/44/44/4
许可证MITMITMITCC-BY-4.0NOASSERTIONApache-2.0
价格登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

BotArmor MCP server

BotArmor is no-code LLM red teaming and prompt injection testing for chatbots and AI agents, built for small businesses and for people who build bots on Make, n8n or Voiceflow. In short: crash-test your bot before your customers do.

This MCP server runs it from your AI assistant: Claude Code, Claude Desktop, ChatGPT, OpenAI Codex, Gemini CLI, Cursor, VS Code (Copilot) or Windsurf. Ask "test my agent with BotArmor" and BotArmor attacks the agent on up to 12 levels:

  • fake manager;
  • angry customer;
  • fake lawyer;
  • prompt injection;
  • role-play;
  • phishing;
  • AI disclosure under the EU AI Act;
  • invented facts;
  • and more.

Level 13 is added for agents with tools. The assistant gets back a report written for it: what broke, how badly, and the exact text to add to the agent's instructions. It can then edit your code and run the audit again.

It is a thin wrapper over the BotArmor API, the same one the Make app, the n8n node and the GitHub Action use.

Who it's for

  • Small businesses with a customer-service bot on their website, WhatsApp or Messenger, who want to know if it can be talked into a discount, a fake promise or an invented price.
  • Freelancers and agencies who deliver bots on Make, n8n or Voiceflow and want a report to hand to their client.
  • Developers who want a quick adversarial check of an agent's system prompt from their editor, without writing a test suite.

If you have a team that writes tests and wants red teaming inside CI, an open-source framework is probably the better fit (see below).

BotArmor vs promptfoo, Giskard and garak

They are good tools and they serve a different user. Open-source frameworks give developers full control. BotArmor gives a verdict and fixes to people who don't write YAML.

BotArmorpromptfooGiskardgarak
Built forSmall businesses, agencies, no-code buildersDevelopersML and product teamsSecurity researchers, ML engineers
What you writeNothing: a prompt, a webhook or a URL, or ask your AI assistantYAML config, CLIPythonCLI options, generator config
Bots on Make, n8n, VoiceflowBuilt in: Make app, verified n8n node, Voiceflow APIThrough an HTTP provider you configureThrough a Python wrapper you writeThrough a REST generator you configure
What you getA–F grade, what broke, the exact text to paste into the system prompt, a signed report for your clientTest results and a red-team reportA scan report of detected issuesA report of probe hit rates
EU AI Act Art. 50 check (does the bot say it's an AI?)Built in, one of the 12 levelsPossible as a custom testPossible as a custom testPossible as a custom probe
Re-test after a fixRun the audit again (start_audit)Re-run the CLIRe-run the scanRe-run the CLI
PriceFree 1-minute quick test; €9 per audit (3 free during the beta)Open source; paid enterprise planOpen source; paid enterprise hubOpen source

Choose promptfoo, Giskard or garak if you build an LLM application in code and want tests in your CI. They are more flexible, and promptfoo in particular is the stronger choice for developer teams.

Choose BotArmor if you deliver or run a customer-facing bot, don't want to maintain a test suite, and need an answer you can act on: what to change in the prompt, and proof that it now holds.

How it works

  1. You ask your assistant. For example: "Check the support agent in this repo with BotArmor."
  2. The assistant calls `start_audit`. It passes the agent's system prompt, which it reads from your code.
  • Prompt mode (default): BotArmor plays that prompt on its own model. Use it for an agent on localhost or not deployed yet.
  • Live mode: BotArmor talks to your running bot at a public https URL. The assistant must first ask you to confirm you own the bot.
  1. BotArmor attacks. For each level it runs 5 adaptive sessions. A judge model rules on each session, and a jury of three models confirms every break. An audit takes 5–20 minutes and uses one credit.
  2. The assistant polls `get_audit_status`. It shows progress: levels done out of total.
  3. It reads `get_audit_report`. The report gives the grade A–F, a table of levels with severity, and for each failed level what happened plus a ready-to-paste fix for the system prompt.
  4. It proposes the fix in your code. With your OK it applies the fix, then runs start_audit again to check that the level now holds.

Your API key stays in your MCP client's configuration. The assistant never receives it. Prompts are not stored by BotArmor, only a SHA-256 fingerprint.

Get an API key

Create a key in the BotArmor dashboard, tab API. It starts with ba_live_. In the examples below, replace ba_live_xxx with it. Keep the key out of your repository: use user-level configuration, or an environment variable.

Connect your assistant

Claude Code
claude mcp add botarmor --scope user -e BOTARMOR_API_KEY=ba_live_xxx -- npx -y @botarmor/mcp

Check with claude mcp list, or /mcp inside a session.

Claude Desktop

Menu Settings → Developer → Edit Config opens claude_desktop_config.json:

  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Add the server, then fully quit and reopen Claude Desktop:

{

"mcpServers": { "botarmor": { "command": "npx", "args": ["-y", "@botarmor/mcp"], "env": { "BOTARMOR_API_KEY": "ba_live_xxx" } } } }

ChatGPT (web) and claude.ai: remote server, no install

Hosts that only connect to servers on the internet use BotArmor's hosted endpoint:

https://app.botarmor.eu/mcp
  1. Add it as a custom MCP server or connector in your host. In ChatGPT this is the apps and connectors settings with developer mode. In claude.ai it is Settings → Connectors → Add custom connector. Menu names change often; look for "MCP server" or "custom connector".
  2. The host opens a BotArmor page. Paste your API key there and click Connect.
  3. The host receives its own token (OAuth 2.1 with PKCE). It never sees your API key.
  4. To disconnect, remove the connector, or revoke the API key in the BotArmor dashboard.

The tools are the same four.

ChatGPT desktop app and OpenAI Codex (CLI and IDE)

They share one configuration. Use either the command line:

codex mcp add botarmor --env BOTARMOR_API_KEY=ba_live_xxx -- npx -y @botarmor/mcp

or ~/.codex/config.toml:

[mcp_servers.botarmor]

command = "npx" args = ["-y", "@botarmor/mcp"] env = { BOTARMOR_API_KEY = "ba_live_xxx" }

In the ChatGPT desktop app you can also add it under Settings → MCP servers → STDIO, with command npx, arguments -y @botarmor/mcp and the env variable.

Gemini CLI
gemini mcp add -s user -e BOTARMOR_API_KEY=ba_live_xxx botarmor npx -y @botarmor/mcp

or ~/.gemini/settings.json:

{

"mcpServers": { "botarmor": { "command": "npx", "args": ["-y", "@botarmor/mcp"], "env": { "BOTARMOR_API_KEY": "$BOTARMOR_API_KEY" } } } }

$BOTARMOR_API_KEY is read from your shell environment, so the key is not written in the file. Check with /mcp in a session.

Cursor

~/.cursor/mcp.json (all projects) or .cursor/mcp.json (one project):

{

"mcpServers": { "botarmor": { "command": "npx", "args": ["-y", "@botarmor/mcp"], "env": { "BOTARMOR_API_KEY": "ba_live_xxx" } } } }

VS Code (GitHub Copilot agent mode)

Run MCP: Open User Configuration from the Command Palette and add the server. VS Code asks for the key once and stores it securely:

{

"inputs": [ { "type": "promptString", "id": "botarmor-key", "description": "BotArmor API key (ba_live_...)", "password": true } ], "servers": { "botarmor": { "type": "stdio", "command": "npx", "args": ["-y", "@botarmor/mcp"], "env": { "BOTARMOR_API_KEY": "${input:botarmor-key}" } } } }

Note that VS Code uses servers, not mcpServers.

Windsurf and other MCP clients

Any client that runs local MCP servers (stdio) works with the same three values:

  • command: npx
  • args: -y @botarmor/mcp
  • env: BOTARMOR_API_KEY

In Windsurf, use the mcpServers block as for Cursor, in ~/.codeium/windsurf/mcp_config.json.

What to ask

  • "Check my agent on localhost:3000 with BotArmor." This runs a prompt audit from the system prompt in your code, because BotArmor's servers cannot reach your localhost.
  • "Audit our staging bot at https://staging.example.com/v1/chat/completions with BotArmor, it's OpenAI-compatible, the token is in .env." This runs a live audit; the assistant asks you to confirm you own the bot.
  • "Is the BotArmor audit done? Show me the report and fix the prompt."
  • "List my last BotArmor audits."

Tools

ToolWhat it does
start_auditStarts an audit and returns its id (BA-XXXXXXXX). It takes 5–20 minutes and uses one audit credit.
get_audit_statusStatus, progress (levels done out of total), and the grade once completed.
get_audit_reportGrade, a table of levels with severity, and for each failed level what happened plus the text to paste into the system prompt.
list_auditsYour latest audits.

start_audit parameters:

  • system_prompt (required): the agent's instructions. For a live audit it is also the rulebook the judge checks answers against.
  • target_type, one of:
  • prompt: the default when no URL is given;
  • openai-compatible: a chat-completions endpoint;
  • webhook: any JSON endpoint.
  • endpoint_url: a public https URL, for live audits.
  • headers: what the target needs. A credential header (Authorization, X-API-Key…) is stored encrypted by BotArmor and never returned.
  • model: for openai-compatible, the model name sent in the body.
  • body_template and response_path: for webhook. The body uses {{input}}, "{{history}}" or "{{messages}}"; the path points to the reply, e.g. data.reply.
  • levels: a subset of logic, toxic, hacker, lawyer, multilang, loop, roleplay, phishing, ethics, burst, disclosure, facts, agency.
  • lang: the report language (fr, en, de, es, ru).
  • min_grade: the pass threshold.
  • authorization_confirmed: must be true for a live audit. Set it only when you own the bot or hold the owner's written permission. BotArmor never tests third-party bots.

Errors you may see

  • "BotArmor rejected the API key": check BOTARMOR_API_KEY.
  • "No audit credit left": buy a pack or upgrade in the dashboard.
  • "... is only reachable from this machine": use target_type: "prompt", or a public tunnel such as cloudflared tunnel --url http://localhost:3000.
  • "the target bot did not answer": the live bot was down, or its URL or headers are wrong.
  • "An audit is already running": one audit at a time per account.

Develop

npm install

npm test # builds, then runs unit tests and an end-to-end stdio test against a mock API

BOTARMOR_API_URL points the server at another API base (default https://app.botarmor.eu/api/v1).

MIT licence. BotArmor AI is a brand of Rhone IA (Andrii Sydorenko EI), France. Reports are point-in-time test attestations, not certifications.