Designforyou

org.swapp1990.designforyou由 designforyou.swapp1990.org 發布官方發布者v1.0.1更新於 Oct 24, 2026

Generate logos, social posts, app screenshots, comic panels & visual-novel assets from prompts.

已驗證Streamable HTTP可網頁執行媒體與設計AI 與機器學習

概覽

AI 產生的概覽

一個託管的設計生成服務,讓助理瀏覽範本,並依提示詞生成標誌、社群貼文、應用程式截圖、漫畫與視覺小說素材。

可以做什麼
瀏覽 119 個設計範本目錄,依標誌、Instagram、應用程式商店截圖等類別篩選並取得推薦;生成前可查看範本的可編輯文字欄位。依選定範本與描述生成成品設計,也可從結構化需求建立私有可重複使用的範本。生成視覺小說角色立繪表,自動裁切儲存格、去除背景並回傳可用清單。創作 Living Panels 互動漫畫:依一段設定寫出 5 頁漫畫、提交由用戶端撰寫的故事 JSON、查詢素材生成進度並進行定向修訂。查詢帳戶的點數餘額、用量與訂閱狀態。
適用情境
適合讓助理把簡短需求變成成品行銷或創意視覺,例如標誌、社群貼文與應用程式商店截圖,或在對話中直接產出漫畫與視覺小說素材。瀏覽與推薦工具免費,可先探索範本目錄再決定是否消耗點數。
執行需求
遠端 Streamable HTTP 端點,託管服務不需本機安裝套件。需要身分驗證:通常透過瀏覽器 OAuth 登入,無介面用戶端可改用 DESIGNFORYOU_MCP_TOKEN 中的長期權杖。生成依點數計費,註冊贈送 50 點,可在網站儲值。選用的本機 sidecar 透過 npx 執行,需要已安裝並登入的 Grok CLI。
安裝前請注意
付費工具會消耗點數:生成、變體、文字編輯與立繪表皆計費,立繪表基本費用為 3 點。DESIGNFORYOU_MCP_TOKEN 是長期憑證,需妥善保管。提示詞與需求會傳送給第三方託管服務。選用的 Grok sidecar 以自動核准工具的方式無介面執行 Grok,只應使用可信提示詞,其媒體生成會另行計入 xAI 帳戶用量,不受聊天訂閱涵蓋。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Designforyou,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。

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/org.swapp1990.designforyou%2Fdesignforyou/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。

{
  "mcpServers": {
    "designforyou": {
      "type": "http",
      "url": "https://designforyou.swapp1990.org/mcp/v2/"
    }
  }
}

README

DesignForYou — MCP server

[npm] [MCP Registry] [License: MIT]

Generate logos, social posts, app-store screenshots, comic panels, and visual-novel assets from natural-language prompts — directly inside Claude Code, Grok, Codex, Cursor, OpenCode, ChatGPT, or any MCP client.

DesignForYou is an MCP-native design generator backed by 119 templates. Browse and recommend tools are free; generation is metered per user (50 free credits on sign-up).

Demo

[DesignForYou demo — prompt to generated design]

Describe what you want → the agent picks a template and generates a finished design. Logos, Instagram posts, app-store screenshots, and more.

Websitehttps://designforyou.swapp1990.org
Connect (human)https://designforyou.swapp1990.org/connect
Agent guide (plain text)https://designforyou.swapp1990.org/.well-known/mcp/connect.md
MCP URLhttps://designforyou.swapp1990.org/mcp/v2/ (trailing slash required)
Privacyhttps://designforyou.swapp1990.org/privacy

Auth

PathWhat you doWho stores secrets
OAuth (primary)Complete browser sign-in when the client promptsThe MCP client
Long-lived token (fallback)Sign in on the website → Generate on /connect → DESIGNFORYOU_MCP_TOKENYou (env / header)

OAuth is the normal path. PAT minting is only for Codex, headless agents, or when OAuth stays “disabled / not connected.” Full recipes: CONNECT.md or the live well-known guide above.

Install

Claude Code (recommended)

bash
claude mcp add --transport http designforyou https://designforyou.swapp1990.org/mcp/v2/claude mcp login designforyou

Approve the browser sign-in when prompted.

Grok

bash
grok mcp add --transport http designforyou https://designforyou.swapp1990.org/mcp/v2/

Then /mcps → designforyou → i (authorize) → browser → r.

OpenCode

Add a remote MCP entry for the URL above, then:

bash
opencode mcp auth designforyouopencode mcp list

Codex (bearer fallback)

  1. Generate a token at https://designforyou.swapp1990.org/connect
  2. Store as DESIGNFORYOU_MCP_TOKEN
  3. Configure:
powershell
codex mcp add designforyou --url https://designforyou.swapp1990.org/mcp/v2/ --bearer-token-env-var DESIGNFORYOU_MCP_TOKEN

Cursor

[Add to Cursor]

Or .cursor/mcp.json:

json
{  "mcpServers": {    "designforyou": {      "url": "https://designforyou.swapp1990.org/mcp/v2/",      "transport": "http"    }  }}

VS Code

[Install in VS Code]

Claude Desktop / stdio shim

bash
npx -y designforyou-mcp

Or native HTTP in claude_desktop_config.json with the /mcp/v2/ URL. Complete OAuth when prompted.

Optional local Grok CLI sidecar

The default command above always uses the hosted DesignForYou MCP server. To run the focused local image and reference-animation tools instead, explicitly opt in with an installed, signed-in Grok Build CLI:

powershell
$env:DESIGNFORYOU_PROVIDER = "grok-subscription"npx -y designforyou-mcp

This sidecar invokes grok --single through the CLI's existing signed-in session; it never accepts or forwards an xAI API key, and it denies all MCP tools inside the spawned CLI so generation cannot route through a hosted billing server. Billing note: the Grok Build CLI's native media tools (image_gen, image_to_video) call the xAI API (api.x.ai) with the signed-in session token, so each generation meters the account's xAI console usage — media generation is not covered by the grok.com chat subscription. The sidecar exposes grok_generate_image and animate_reference_grok_video, and verifies the requested local output file before returning it. The hosted tools and their providers remain the default when the variable is unset. (The grok-subscription opt-in value is kept for compatibility with existing client configs.)

Use the sidecar from local Codex threads

Register the checked-out sidecar as a local stdio MCP server:

powershell
codex mcp add designforyou-grok-local `  --env DESIGNFORYOU_PROVIDER=grok-subscription `  -- node D:\MyProjects\Claude\designforyou-mcp\bin.js
codex mcp list

Restart Codex or open a new local thread after adding the server. The thread can then generate a starting frame with grok_generate_image and pass that file to animate_reference_grok_video for an acting performance:

json
{  "image_path": "D:\\assets\\actor-scene.jpg",  "prompt": "She notices someone entering, freezes, then forces a nervous smile. Step backward slowly while maintaining eye contact. Use a subtle handheld push-in.",  "line": "I wasn't expecting you.",  "duration": 6,  "aspect_ratio": "16:9",  "output_path": "D:\\assets\\performance.mp4"}

The reference may be supplied as image_path, image_url, or image_data_url. This is a local-development path: the Codex host must be able to run the installed, signed-in grok executable. Codex cloud threads cannot use the machine's Grok login or local files. Use only trusted prompts because the sidecar runs Grok headlessly with automatic tool approval.

For video results, public_url is returned when Grok supplies a usable URL/key or when optional S3 correlation is configured. The sidecar brackets generation with S3 listings and accepts only one newly-created object whose key is absent from the baseline and whose byte size exactly matches the verified local MP4; it also checks HTTP accessibility. S3 settings can be supplied with DESIGNFORYOU_GROK_S3_BUCKET, DESIGNFORYOU_GROK_S3_REGION, DESIGNFORYOU_GROK_S3_ENDPOINT, and DESIGNFORYOU_GROK_S3_KEY_PREFIX, or discovered from the narrowly-scoped [tools.zdr_video_output_s3] and its .read_write credentials section in the local Grok config. Missing configuration, listing failures, ambiguous matches, and inaccessible objects leave the verified local success intact and include a diagnostic. Automatic correlation requires the AWS CLI on PATH and the local Grok S3 configuration. The configured identity also needs s3:ListBucket restricted to the configured key prefix; upload-only s3:PutObject credentials cannot perform safe correlation. Credentials are passed only to the AWS child process and are never printed or packaged. If listing is unavailable, generation still returns the verified local file with an explicit diagnostic.

Tools

ToolCostWhat it does
browse_templatesfreeBrowse the 119-template catalog (filter by category)
recommend_templatefreeRecommend the best templates for a described use case
get_text_fieldsfreeList a template's editable text fields
get_creditsfreeCheck your credit balance
generatepaidGenerate a finished design from a template + description
generate_variationspaidGenerate style variations of a template
edit_textpaidEdit text on an existing design
vn_generate_sprite_sheetpaidGenerate a visual-novel character sprite sheet

Example prompts

  • "Browse logo templates on DesignForYou."
  • "I'm opening a coffee shop called NEXUS — minimalist, warm earth tones. Make me a logo."
  • "Generate an Instagram post announcing a 20%-off flash sale for a vegan bakery."
  • "Create an app-store screenshot for a meditation app, calm gradient background."

How it works

DesignForYou exposes a remote MCP server (Streamable HTTP). On the first paid tool call (or when you run mcp login / mcp auth), your client discovers the OAuth flow (RFC 9728 protected-resource metadata → Supabase with Dynamic Client Registration), opens a browser for sign-in + consent, and stores tokens. Generation is metered against your credit balance; top up on the website.

This repository is the public home for install docs and the MCP server.json. The product itself is a hosted service — there is no self-host package.

Links

來源:README.md,提交 a015e8c

工具

14

browse_templates

Browse templates

Browse the DesignForYou template catalog. Optionally filter by category (e.g. 'instagram', 'app-store', 'logo', 'living-panels'). Returns template IDs, names, and previews.

輸入參數categorysubcategory

recommend_template

Recommend a template

Recommend the best matching templates for any use case. Describe what you need and the system auto-detects the category and ranks templates by relevance. Return the recommendations so the user can pick a template from the visual gallery; do not call `generate` in the same turn unless the user explicitly names a template_id or asks you to skip selection.

輸入參數needscategoryuse_case必填subcategory

widget_diagnostic

Test widget rendering

Return a fixed, no-cost DesignForYou widget payload for ChatGPT Apps debugging. Use this only to verify the template gallery/result iframe renders correctly; it does not generate images, use an LLM, or charge credits.

輸入參數mode

get_text_fields

Get template text fields

List a template's editable text fields (headline, subhead, CTA, etc.) with their current values. Free. Use right after a template is chosen and BEFORE `generate` when you want to fill the template's fields precisely instead of relying on a freeform description.

輸入參數template_id必填

generate

Generate design

Generate one or more finished images from a template (get a template_id from recommend_template or browse_templates) plus a description. Use this after the user has selected or explicitly supplied a template_id; otherwise call `recommend_template` first so the visual gallery can collect the selection. Works for all categories (Instagram, logo, app-store, Visual Novel backgrounds/sprites, CG illustrations). Pass variants for multi-image output (expressions, time-of-day, etc.). Pass session_id to refine a prior result. Pass context_ids to ground a new image on prior designs (character consistency for VN CG scenes). Set model to 'minimax-h3-image-balanced' or 'minimax-h3-image-quality' (or use the 'h3 balanced'/'h3 quality' aliases) to render through the MiniMax H3 image service; context_ids are forwarded as ordered H3 reference images.

輸入參數modelvariantsedit_tiersession_idcontext_idsdescription必填template_id必填context_labelsreference_urlsreference_rolesreference_labelsskip_prompt_merge

vn_generate_sprite_sheet

Generate VN sprite sheet

Generate one fixed-grid visual-novel character sprite sheet, crop it into cell assets, remove the chroma-key background, validate transparent sprites, and return a VN Creator-ready manifest. Base cost: 3 credits. Optional quality.hi_res_cells=true adds a reference-grounded per-cell re-render at full native resolution (fixes cells being limited to ~1/N of the sheet resolution) and bills +2 credits per cell re-rendered. quality.hi_res_model optionally routes the hi-res pass to a specific model (e.g. gpt-image-2 for fabric fidelity).

輸入參數cells必填modelsheet必填style必填outputqualityprovidercharacter必填

comic_design_brief

Get comic design brief

Return the no-server-LLM Living Panels authoring brief: PanelScript instructions, schema, unit templates, and success criteria. Use this when the MCP client will do the creative direction with its own model, then call comic_submit_design with the authored Story JSON.

輸入參數premise必填

comic_submit_design

Submit client-directed comic

Accept a client-authored Living Panels Story JSON and start artifact production without using a server story LLM. The client does direction; DesignForYou validates, saves, generates character sheets, panel/unit art, motion clips, voice-over, and assembles the public reader.

輸入參數story必填premise必填client_nameclient_modelstart_production

create_template

Create private reusable template

Create a private reusable DesignForYou template from a structured brief. The returned template_id works immediately with get_text_fields and generate. This stores a user-owned template in the canonical catalog collection; it does not publish it to the anonymous gallery.

輸入參數name必填width必填height必填best_forcategory必填base_prompt必填subcategorytext_fields必填aspect_ratio必填layout_rules必填

create_comic

Create living comic

Write and produce a Living Panels interactive comic from a one-paragraph premise. One call writes a complete 5-page comic (panels, dialogue, motion plan, voice casting) and starts generating every asset in the background: character sheet, ~13 panels of art with character consistency, ambient image-to-video motion for the liveliest panels, and per-line voice-over. Returns immediately with the story summary and a public reader_url where the comic can be read, watched live, and heard. Production takes several minutes — poll comic_status until ready, then share the reader_url.

輸入參數premise必填

comic_status

Check comic production

Check asset-production progress for a comic created with create_comic: panels, motion clips, and voice lines done vs total, plus ready=true when the whole comic is live at its reader_url. Free to call.

輸入參數comic_id必填

comic_revision_brief

Get comic revision brief

Return the current Story JSON, stale-write hash, allowed patch paths, and dirty-node contract for a client-authored Living Panels revision. Use this when the client will decide the edit with its own model, then call comic_submit_revision.

輸入參數comic_id必填

comic_submit_revision

Submit client comic revision

Apply a client-authored Living Panels revision without using a server revision LLM. Targeted changes regenerate only inferred dirty producer nodes such as panel:<id>, motion:<id>, or tts:<bubble_id>.

輸入參數storychangessummarycomic_id必填client_namedirty_nodesclient_modelbase_story_hash必填start_production

get_credits

Check credit balance

Return the authenticated user's current credit balance, usage, and Stripe subscription status. Free to call.

無需輸入參數。

版本歷史

1
  1. v1.0.1最新Sep 16, 2026

評分

已滿足適用檢查項的 100%

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