Gency Mcp

ai.gency由 gency.ai 發布v0.7.0更新於 Oct 29, 2026

Gency AI product image generation - MCP server for Claude, Codex, Cursor, VS Code

發布方自己的服務:Gency Lite

已驗證STDIO僅桌面媒體與設計

概覽

AI 產生的概覽

透過本機 MCP 伺服器讓助理使用 Gency AI 服務生成產品圖片。

可以做什麼
Gency Mcp 是一個本機 stdio MCP 伺服器,把助理連接到 Gency AI 產品圖片生成服務。登錄描述稱其為 Claude、Codex、Cursor、VS Code 等助理提供產品圖片生成。清單未列出個別工具,因此這裡無法說明確切的可用操作。設定透過環境變數完成,涉及 Gency API 基礎網址與 OAuth 設定。
適用情境
當你希望助理不必離開編輯器或聊天用戶端,就能透過 Gency 產生產品圖片時,可以考慮使用。它適合桌面工作流程,因為以本機程序執行且標示為僅限桌面。
執行需求
需要 Node.js 與 npm 套件 @gency-ai/gency-mcp,以 stdio 方式在本機執行。環境變數包括 GENCY_API_URL、GENCY_OAUTH_API_BASE、GENCY_OAUTH_CLIENT_ID、GENCY_OAUTH_SCOPE、GENCY_MCP_ALLOWED_CLIENT_IDS 與 GENCY_MCP_OAUTH_RESOURCE。機密 GENCY_OAUTH_CLIENT_SECRET 僅在機密 OAuth 用戶端時需要,GENCY_MCP_UPLOAD_SECRET 僅在多執行個體 HTTP 服務時需要。需要連線至 Gency API 的網路存取。
安裝前請注意
此伺服器可能要求機密 GENCY_OAUTH_CLIENT_SECRET,多執行個體 HTTP 服務時還要求 GENCY_MCP_UPLOAD_SECRET;兩者都應視為憑證,不要寫入共用設定。圖片生成可能消耗 Gency 付費額度,請先確認方案與上限。生成的圖片與提示詞會傳送給第三方 Gency 服務。清單未列出工具,授權前應先確認伺服器實際能做什麼。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Gency Mcp,將其新增到工作區。
  2. 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

該儲存庫沒有 README。

工具

21

login

Start OAuth login (opens a browser). Captures the callback in-process and stores tokens at ~/.gency/tokens.json. gency-mcp uses OAuth only — this is the single sign-in flow.

輸入參數portscopeapi_baseclient_idclient_secrettimeout_seconds

logout

Remove stored OAuth tokens (~/.gency/tokens.json). gency-mcp is OAuth-only — there is no API key state to clear.

無需輸入參數。

auth_status

Inspect current Gency OAuth state. Call this BEFORE the first gency tool in a session if unsure — output's 'Next action' line tells you whether to invoke `login` or proceed. gency-mcp authenticates with OAuth only.

無需輸入參數。

get_team

Get current team information including team name and plan

無需輸入參數。

list_workspaces

List all workspaces in the current team

無需輸入參數。

create_workspace

Create a new workspace. Confirm with the user before executing.

輸入參數name必填

update_workspace

Rename a workspace. Confirm with the user before executing.

輸入參數name必填workspaceId必填

list_templates

List templates for a workspace (workspace-specific + defaults TEMPLATE_01~TEMPLATE_12). Present as a picklist for the user — do NOT silently pick.

輸入參數productTypeworkspaceId必填

list_products

List products in a workspace.

輸入參數workspaceId必填

get_product

Get detailed information about a specific product.

輸入參數productId必填

create_product

Create AI-generated product images. **Consumes credits — confirm with the user first.** Only `category: "CLOTHING"` is accepted by the API today. Defaults to ONE product per request (all colors go in a single `colors` array; split only on explicit user request). **Do NOT guess colors/fabrics/features/laundryTips from filenames or category — ask the user.** Generation is asynchronous: poll `get_product` until status leaves CREATING. Read resource `gency://api-reference/products` for the full ProductMetadata schema (category enum, additionalInfo, sizeTables format).

輸入參數products必填workspaceId必填

update_product_status

Change product review status. Confirm with the user. Transitions: BEFORE_REVIEW → IN_REVIEW → REVIEW_COMPLETE.

輸入參數status必填productId必填

get_upload_url

Get a presigned S3 URL to upload one product image, plus the uploadHandle that `upload_image` requires. Single-use, valid 1h; uploaded images retained 24h. See `gency://api-reference/images`. Tip: for the common 6+ images case, prefer `prepare_product_images` (single call).

輸入參數extension必填workspaceId必填

download_product_image

Render a generated product's detail page and save the resulting image locally. Requires the product to be generated (status past CREATING). Rendering is slow — allow up to 3 minutes.

輸入參數productId必填outputPathtemplateId

upload_image

PUT a local image file to the presigned S3 URL that get_upload_url issued. Pass the `uploadHandle` from that call — it carries the destination URL, so no URL is accepted here.

輸入參數filePath必填contentTypeuploadHandle必填

prepare_product_images

Upload 6+ local images for a workspace and return imageIds ready for create_product. Use this when the user gives you several image paths — it replaces 6× (get_upload_url + upload_image). Fails fast if fewer than 6 paths are supplied (Gency requires min 6 per product).

輸入參數filePaths必填workspaceId必填

get_me

Get current authenticated user information

無需輸入參數。

list_users

List all team members

無需輸入參數。

get_user

Get information about a specific team member. The target user must belong to the same team as the caller.

輸入參數userId必填

get_credits

Get remaining credit balance for the team. Call this BEFORE create_product to ensure sufficient credits.

無需輸入參數。

search_docs

Search Gency API docs by keyword. Returns top 3 ranked snippets with line numbers from developers.gency.ai (cached 1h).

輸入參數query必填

版本歷史

2
  1. v0.7.0最新Oct 22, 2026
  2. v0.6.0Sep 16, 2026

評分

已滿足適用檢查項的 65%

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
  • 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。

  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分

    請宣告包含 README 的 GitHub 儲存庫,或在 OAuth 受保護資源後設資料中提供 resource_documentation。

  • 授權條款10 分

    請在儲存庫或註冊中心條目中宣告授權條款。

其他 Gency 整合