TOPY.AI · AI CSO

ai.topy由 topy.ai 發布官方發布者v0.1.0更新於 Nov 5, 2026

Founders' AI CSO: vulnerabilities, dependencies, secrets, verified-site checks, threat model, fixes.

發布方自己的服務：TOPY.AI · AI CEO

已驗證Streamable HTTP可網頁執行雲端與基礎設施開發者工具安全與監控

概覽

AI 產生的概覽

TOPY.AI AI CSO 讓編碼助理具備資安長能力：CVE 與相依套件檢查、金鑰掃描、已驗證網站的網頁檢查、威脅模型與事件報告。

可以做什麼
  • 排查是否受指定 CVE 影響，檢查鎖定檔相依套件、停止維護的執行環境，以及安裝前的套件風險
  • 掃描程式碼中的金鑰與不安全模式，產出 STRIDE 威脅模型與 OWASP ASVS 清單
  • 驗證網域擁有權，評比 HTTP 安全標頭、Cookie 與 TLS，並對已驗證網站執行安全掃描
  • 在信任之前審查技能、外掛與 MCP 伺服器，並稽核自家的 MCP 登錄清單
  • 記錄資安事件，產出依風險分級、供人工執行的修復方案，並寄送每週資安報告
適用情境
適合想讓助理持續做資安值守的小團隊或獨立創辦人：每日 CVE 與停止維護提醒、上線前的金鑰與程式碼檢查、每週資安報告。也適合在安裝第三方技能或 MCP 伺服器前先做安全審查。
執行需求
需要 TOPY.AI 帳號並以 OAuth 授權，或提供 TOPY_API_KEY（也可用 npm 套件一次性登入）。可連線 topy.ai 遠端端點，或使用本機 stdio 套件 @topy-ai/cso-mcp 轉送。主機檢查與公開網站檢查需在 OneMan 上由本人授予主機同意。需要網路連線。
安裝前請注意
OAuth 會授權存取你的 TOPY.AI 帳號，只有擁有 OneMan 營運的帳號才看得到其發現結果。伺服器會讀取程式碼、git 歷史與建置產物以找出金鑰，發現結果會上傳至 TOPY.AI。其聲明不會變更伺服器、防火牆或網站，也不會輸出金鑰，但修復方案與掃描結果仍應由人工複核。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 TOPY.AI · AI CSO，將其新增到工作區。
  2. 連接 所需的 憑證。它們會被私密儲存，絕不會在公開頁面上展示。
  3. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/ai.topy%2Fcso/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。 客戶端會在首次連接時完成 OAuth 登入。

{
  "mcpServers": {
    "topy-ai-ai-cso": {
      "type": "http",
      "url": "https://topy.ai/mcp/cso"
    }
  }
}

README

[TOPY AI CSO]

TOPY AI CSO Skills

19 skills that make your coding agent a small company's AI CSO: new CVEs and end-of-life dates for everything you run, no secrets in code, headers, TLS and safe scans of the domains you have verified, every skill and MCP server vetted before it is trusted, incident timelines and a weekly security report to the founder and the CEO — on the TOPY.AI CSO MCP server.

[npm] [MIT License] [MCP]

The AI CSO is goal-first. It keeps five standing goals — no open critical exposure (anything on CISA KEV or critical with a fix is fixed within days), zero secrets in code, verified-only active checks, nothing trusted unvetted (every new skill, MCP server and package checked first) and every incident with a timeline — and every skill below exists to move one of them.

  • Core (topy-ai-cso): connect, first setup (inventory, domain verification, host consent), the CSO's goals, the daily watch.
  • Vulnerabilities: are we affected by this CVE, dependencies and supply chain, end of life, vetting a package before install.
  • Code: secrets (rotate first, then remove), unsafe code patterns, a STRIDE threat model and the OWASP ASVS checklist.
  • Web: domain verification, headers and TLS, a safe scan of a verified site.
  • Agents: vet a skill or MCP server before it is installed (the App Factory gate), and audit your own MCP server.
  • Response: incident timelines, a fix plan with fix-risk tiers T1–T4, the weekly security report.

The safety model comes from Maggie Security and does not bend: the CSO never changes a server, firewall or website (fix and protection plans are for a person to review and apply), never scans a domain you have not verified, reads a server only after you grant consent yourself, by your own approval in the chat (an agent cannot), leaves checks of sites you don't control to a person (never a routine), never uses offensive techniques and never prints a secret. Changes take two calls — a preview, then your yes.

Install

sh
npx @topy-ai/cso-skills install                  # this project, for the agents set up herenpx @topy-ai/cso-skills install -g --mcp         # your user, plus the MCP servernpx @topy-ai/cso-skills install --category vulnerabilities,webnpx @topy-ai/cso-skills list

Claude Code plugins: /plugin marketplace add TOPY-AI-LTD/TOPY-AI-CSO-Skills, then /plugin install topy-ai-cso-all@topy-ai-cso. Codex: codex plugin marketplace add TOPY-AI-LTD/TOPY-AI-CSO-Skills. Pi: pi install npm:@topy-ai/cso-skills. See the installer README.

Connect TOPY.AI

https://topy.ai/mcp/cso — OAuth with your TOPY.AI account (the same one as the AI CEO, CFO and COO). Only the accounts that own the OneMan operation see its findings.

ClientHow
Claude, ChatGPT (web, desktop)custom connector https://topy.ai/mcp/cso
Claude Codeclaude mcp add --transport http topy-cso https://topy.ai/mcp/cso
Codexcodex mcp add topy-cso --url https://topy.ai/mcp/cso
Clients that only start a commandnpx -y @topy-ai/cso-mcp after npx @topy-ai/cso-mcp login
Terminal and scriptsnpm i -g @topy-ai/cso-cli && cso-cli login

Server checks (host-quick, host-audit) and passive checks of sites you don't control (public-check) are not on topy.ai: they need a person on OneMan, with host consent granted by the person's own approval in the chat.

How the skills fit together

topy-cso-connect ─▶ topy-cso-setup (inventory · domain verify · consent) ─▶ topy-cso-goals        │   daily 06:17: topy-cso-daily-watch ─▶ topy-cso-cve-response ─▶ topy-cso-incident ─▶ topy-cso-fix-plan        │                               topy-cso-dependencies · topy-cso-end-of-life   weekly Mon 07:23: topy-cso-weekly-report ─▶ the founder (email) and the CEO        │   before code ships: topy-cso-secrets · topy-cso-code-scan · topy-cso-threat-model   web (verified domains): topy-cso-domain-verify ─▶ topy-cso-web-checks ─▶ topy-cso-web-scan   before you trust it: topy-cso-package-vet · topy-cso-vet-skill · topy-cso-mcp-audit

Try: "Anything new I should worry about?", "Are we affected by CVE-2026-…?", "Did a key leak?", "Is this MCP server safe to install?", "Send the weekly security report"

Packages

PackageWhat it is
@topy-ai/cso-skillsThis installer (Claude Code, Codex, Pi, Cursor, Gemini CLI, …)
@topy-ai/cso-mcpThe CSO MCP server as a local stdio server (forwards to https://topy.ai/mcp/cso)
@topy-ai/cso-cliThe AI CSO on the command line

Repository structure

plugins/  topy-ai-cso/                   core skills + .mcp.json (Claude Code) and mcp.json (Codex)  topy-ai-cso-vulnerabilities/   topy-ai-cso-code/   topy-ai-cso-web/  topy-ai-cso-agents/            topy-ai-cso-response/  topy-ai-cso-all/               bundle that depends on all six.claude-plugin/marketplace.json     Claude Code marketplace.agents/plugins/marketplace.json    Codex marketplaceskills.json                         machine-readable cataloguepackages/skills/                    the @topy-ai/cso-skills installer

The skills are generated from a source catalogue kept next to TOPY.AI's MCP server; the build checks every tool a skill names against the CSO server's tool list. Please open an issue rather than editing a SKILL.md.

License

MIT © TOPY AI LTD. Privacy: topy.ai/privacy.

Skills

19 skills in 6 plugins, plus the topy-ai-cso-all bundle. Generated from the source catalogue: please open an issue rather than editing a SKILL.md.

AI CSO core (MCP) · topy-ai-cso

SkillTierWhat it does
topy-cso-connectcoreConnect the TOPY CSO MCP server and check what applies: the project's stack, verified domains, granted hosts, tools and feeds.
topy-cso-daily-watchcoreEvery morning: new CVEs, advisories and end-of-life dates for everything the company runs, matched to the stack — quiet unless something new needs a person.
topy-cso-goalscoreThe AI CSO's standing goals and its status report for the CEO: open critical exposure, secrets in code, verified-only checks, vetted skills and MCP servers, incident timelines.
topy-cso-setupcoreFirst run for a new company or site: inventory the stack, verify each domain you own, and explain host consent — so every later check is allowed and complete.

Vulnerabilities & supply chain · topy-ai-cso-vulnerabilities

SkillTierWhat it does
topy-cso-cve-responseconnectedA named CVE or advisory: are we affected, where, how urgent, and the response plan — with an incident timeline from start to close.
topy-cso-dependenciesconnectedKnown vulnerabilities in every lockfile ecosystem and in JavaScript copied into the site, prioritised, with the fixed versions.
topy-cso-end-of-lifeconnectedRuntimes, databases, web servers and operating systems that stopped (or will soon stop) getting security fixes, and what to upgrade to.
topy-cso-package-vetconnectedBefore adding a package: known vulnerabilities and malicious-package reports for that exact version, and a clear install / pin / don't install.

Code & secrets · topy-ai-cso-code

SkillTierWhat it does
topy-cso-code-scanconnectedUnsafe code patterns before they ship — injection, unsafe deserialisation, personal data in logs, weak crypto — with the safe pattern for each.
topy-cso-secretsconnectedKeys, tokens and passwords in the code, its git history and the build output — and the rotate-first fix for each.
topy-cso-threat-modelconnectedA STRIDE threat model of the system and an OWASP ASVS checklist filled from the findings — what could go wrong and how far we meet the standard.

Web surface · topy-ai-cso-web

SkillTierWhat it does
topy-cso-domain-verifyconnectedProve the company controls a domain (DNS TXT record or a token file) before any active check — the CSO never scans a site that isn't verified.
topy-cso-web-checksconnectedGrade a verified site's HTTP security headers and cookies (A+ to F) and its TLS (protocols, certificate trust and expiry), with the exact fix for each.
topy-cso-web-scanconnectedA safe, rate-limited vulnerability scan (known flaws, exposed files, misconfigurations) of a site the company has verified — never exploitation.

Agent & MCP security · topy-ai-cso-agents

SkillTierWhat it does
topy-cso-mcp-auditconnectedOWASP MCP checks on the company's own MCP tool registry: read-only hints, destructive tools behind confirmation, scopes, audit logging and hosts it may call.
topy-cso-vet-skillconnectedBefore a skill, plugin or MCP server is installed or published: prompt-injection, data exfiltration, over-broad permissions and risky tools — the App Factory security gate.

Response & reporting · topy-ai-cso-response

SkillTierWhat it does
topy-cso-fix-planconnectedTurn the findings into a reviewed runbook — each action tagged T1 (batch-safe) to T4 (stage first) — that a person reviews and runs. The CSO never applies it.
topy-cso-incidentconnectedRecord a security incident or CVE response from start to close — what happened, every step and who did it — so nothing is lost and the report writes itself.
topy-cso-weekly-reportconnectedEvery Monday: what is open by priority, what was fixed, what changed in the stack, and at most three actions — for the Founder by email and for the CEO.

來源：README.md，提交 40cbf4e

工具

0
該伺服器需要登入，因此 SourceWeft 無法在沒有帳號的情況下讀取其工具，也未收錄。已連接帳號所能看到的內容可能因帳號及其權限而異。

版本歷史

1
  1. v0.1.0最新Oct 29, 2026

評分

已滿足適用檢查項的 85%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list，或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

其他 Topy 整合

TOPY.AI · AI CEO

ai.topy官方發布者

TOPY.AI 的 AI CEO MCP 伺服器，讓助理撰寫並維護創辦人的商業計畫、CEO 紀錄、募資與財務工作。

Streamable HTTP可網頁執行驗證方式
效率與工作流需要憑證Oct 26, 2026

TOPY.AI · AI CTO

ai.topy官方發布者

TOPY.AI AI CTO 讓程式開發助理透過 GitHub 處理 CI 失敗、PR 審查、發布、部署與安全告警，扮演小型團隊的 AI 技術長。

Streamable HTTP可網頁執行驗證方式
雲端與基礎設施需要憑證Oct 29, 2026

TOPY.AI · AI CRO

ai.topy官方發布者

遠端或本機執行的 MCP 伺服器，為助理提供小型公司的 AI CRO：依真實數據做營收檢視、銷售管道、交易台、報價與催收。

Streamable HTTP可網頁執行驗證方式
效率與工作流需要憑證Oct 29, 2026

TOPY.AI · AI CPO

ai.topy官方發布者

TOPY.AI AI CPO 讓助理具備產品管理能力：回饋分流、優先順序排序、PRD、預先註冊實驗與決策日誌。

Streamable HTTP可網頁執行驗證方式
效率與工作流需要憑證Oct 29, 2026

TOPY.AI · AI COO

ai.topy官方發布者

TOPY.AI 的 AI COO 伺服器，讓助理監控 AI 共同創辦人的排程 Routine、失敗、審批與每週營運報告。

Streamable HTTP可網頁執行驗證方式
效率與工作流需要憑證Oct 29, 2026