
Caelo CMS
io.github.caelo-cms由 GitHub 帳號 caelo-cms 發布v0.11.21更新於 Nov 6, 2026
Edit a self-hosted Caelo CMS site from your agent. Changes land in a draft; a human publishes.
概覽
讓 AI 助理透過對話或直接管理工具編輯自架的 Caelo CMS 網站,變更先進入草稿,由人工發布。
- 可以做什麼
- 向 Caelo 內建的 AI 代理傳送訊息、延續工作階段,並可附上頁面脈絡與圖片
- 透過對話瀏覽、發布與提出網站變更,具備稽核紀錄與 Owner 核准關卡
- 在 admin 模式下直接呼叫完整工具目錄,由你自己的代理驅動工具迴圈
- 從本機路徑或 base64 上傳圖片到共用的 CMS 媒體庫
- 匯出依安裝即時脈絡產生的 CLAUDE.md 與技能目錄
- 適用情境
- 適合自架 Caelo CMS 的使用者,想讓代理起草、修改或檢視網站內容,同時保留人工發布控制。適用於 Claude Code、Cursor、VS Code 等桌面 MCP 用戶端,而非瀏覽器內的助理。
- 執行需求
- 需要本機執行環境與 bunx(Bun)來啟動 stdio 伺服器,以及可連線的 Caelo 管理站台。需設定 CAELO_ADMIN_URL(https,僅 localhost 可用 http)與由 Owner 在 /settings/mcp 產生的 CAELO_MCP_TOKEN。Google Cloud IAP 安裝另需 CAELO_IAP_SERVICE_ACCOUNT 及透過 gcloud 登入取得的 Application Default Credentials。桌面應用程式需填入 bunx 的完整路徑。
安裝
在 SourceWeft 中
- 開啟 儀表板中的 Caelo CMS,將其新增到工作區。
- 為需要使用其工具的對話啟用該服務。
Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。
其他 MCP 客戶端
參照 儲存庫 中的啟動說明。
README
@caelo-cms/mcp-server
MCP servers for your Caelo CMS install. Two surfaces, selected by the token's scope:
caelo_chat(default mode, scopechat) — talks to Caelo's own AI agent. You describe an outcome; Caelo's chat-runner does the work.- Power-MCP (
caelo-admin-mcpbinary /caelo-mcp-server admin, scopeadmin) — the full chat-runner tool catalogue exposed directly, so YOUR agent (Claude Code et al.) drives the tool loop and Caelo makes no provider calls of its own.caelo-mcp-server exportadditionally writes a CLAUDE.md +.claude/skills/tree generated from the install's live context.
Every mode is a thin shim: calls become HTTPS POSTs against your admin
install's /api/mcp/* endpoints, which dispatch into the same
chat-runner machinery that powers the live-edit overlay. See the
MCP page in the docs for the full Power-MCP working
model (work sessions, the shared draft, approval gates).
Install
In your Caelo install:
- Visit
/settings/mcpas an Owner. - Click New token, give it a name (
claude-code,laptop,ci, etc.), optionally set an AI-spend cap (microcents), and copy the bearer that's shown ONCE. - The page shows ready-to-copy setup for Claude Code, Claude Desktop, Codex CLI, Cursor, VS Code and Gemini CLI — a terminal command or a JSON config entry, plus how the client picks it up.
Desktop apps (Claude Desktop, Cursor, VS Code) don't inherit your
terminal's PATH: put the full path of bunx (which bunx) into their
config instead of the bare name.
ChatGPT and claude.ai in the browser can't use this server: they only connect to MCP servers hosted on the internet (Streamable HTTP + OAuth), and this one runs on your machine over stdio. Tracked in #806.
Manual setup for any other MCP-aware client:
It switches to the exact release your install runs at startup (see the
MCP page in the docs), so the command never needs a
version; @latest keeps bunx from reusing an older cached install.
with these env vars set:
Without CAELO_ADMIN_URL or CAELO_MCP_TOKEN the server still starts and
lists its tools (MCP directories inspect servers that way), but every
tool call fails and names the variable to set. Power-MCP then lists the
catalogue shipped with this release (power-catalogue.json); once
configured it always lists your admin's live catalogue, including plugin
tools. export exits instead.
Installs behind Google IAP (GCP)
On gcp and gcp-firebase installs the admin sits behind Identity-Aware Proxy, which rejects every request before Caelo sees it unless it carries a Google credential. With CAELO_IAP_SERVICE_ACCOUNT set, the server signs a short-lived JWT as that service account (IAM Credentials signJwt, using your Application Default Credentials) and sends it in Authorization next to x-caelo-mcp-token: IAP checks the first, Caelo the second.
One-time setup on your machine:
The provisioner creates the service account (caelo-mcp@<project>), allowlists it on IAP and lets everyone on the IAP allowlist sign as it — on new installs via Pulumi, on existing ones during cms-provision upgrade. No service-account keys are involved.
The caelo_chat tool
Output: assistant reply text + a JSON block with chatSessionId (for
the next call), requestId (click through to
/settings/audit/<requestId> for the full audit trail), the structured
tool-call summaries the agent dispatched, the per-turn cost in
microcents, and a pendingProposals count so the agent can surface
"you have N things waiting for Owner approval".
Why route editing through chat?
Browse / publish / propose actions happen through the chat — "which
pages exist?" → the Caelo agent calls pages.list internally → answers
in text. Same auth surface, same RLS scoping, same audit trail, same
propose-execute Owner gate as the browser. The remote agent talks to a
human-equivalent agent, not to a programmatic API.
License
MPL-2.0.
Image uploads
Both modes expose caelo_upload_images. For example, call it with:
Paths are local to the MCP process. Alternatively use base64 plus an optional filename; supply exactly one of filePath and base64. Uploads support PNG/JPEG/WebP/GIF, up to 5 MiB each, with at most four files per call. The result contains per-file successes/errors and an attachments array. Pass that array to caelo_chat alongside message to send actual image content to Caelo's AI. In admin mode, the returned asset IDs can be used with regular media/page tools.
The token owner's current content.write permission is required for either scope. Images are stored in the shared CMS media library; admin previews require authentication. Uploading alone does not publish a page. A partial batch keeps successful uploads — retry only the failed entries. See the MCP page in the docs for HTTP examples and server limits.
來源:packages/mcp-server/README.md,提交 1149615
工具
0版本歷史
25- v0.11.21最新Nov 6, 2026
- v0.11.20Nov 5, 2026
- v0.11.19Nov 5, 2026
- v0.11.17Nov 5, 2026
- v0.11.15Nov 4, 2026
- v0.11.12Nov 4, 2026
- v0.11.11Nov 3, 2026
- v0.11.10Nov 3, 2026
- v0.11.7Nov 1, 2026
- v0.11.6Oct 31, 2026
- v0.11.5Oct 30, 2026
- v0.11.4Oct 30, 2026
- v0.11.3Oct 29, 2026
- v0.11.0Oct 26, 2026
- v0.10.72Oct 25, 2026
- v0.10.71Oct 25, 2026
- v0.10.68Oct 24, 2026
- v0.10.67Oct 23, 2026
- v0.10.65Oct 23, 2026
- v0.10.64Oct 22, 2026
- v0.10.62Oct 21, 2026
- v0.10.61Oct 21, 2026
- v0.10.60Oct 21, 2026
- v0.10.59Oct 20, 2026
- v0.10.58Oct 20, 2026
評分
已滿足適用檢查項的 50%
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25 分
請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。
- 已宣告認證方式10 分
請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。
- 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