Pixelvault

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

• 连接方式: 在云端运行
• 传输方式: Streamable HTTP
• 分类: 设计、图片与音频
• 你需要填写：Authorization

安装

选择你使用的 AI 应用，然后复制设置。

你需要

• 在云端运行无需安装任何东西，通过互联网连接

你用的是哪个应用？

claude mcp add --transport http pixelvault https://mcp.pixelvault.dev/mcp --header 'Authorization: Bearer {pixelvault_api_key}'

{
  "mcpServers": {
    "pixelvault": {
      "url": "https://mcp.pixelvault.dev/mcp",
      "headers": {
        "Authorization": "Bearer {pixelvault_api_key}"
      }
    }
  }
}

{
  "servers": {
    "pixelvault": {
      "type": "http",
      "url": "https://mcp.pixelvault.dev/mcp",
      "headers": {
        "Authorization": "Bearer {pixelvault_api_key}"
      }
    }
  }
}

你的选择通过 Cookie 保存在这台设备上，无需账户。

需要你填写的值

• Authorization 机密 必填 HTTP header
  PixelVault API key sent as a Bearer token. Create one in your dashboard at https://pixelvault.dev.

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。

它能做什么

工具名称和描述与服务器在 2026年11月7日 报告的完全一致。这些内容由作者撰写，不是我们写的；我们以纯文本形式显示。

• get_image

  Get metadata (CDN URL, size, MIME type, dimensions) for one PixelVault image by id. Maps to GET /v1/images/:id. Requires a PixelVault API key sent as a Bearer token in the Authorization header. The returned CDN URL supports on-the-fly transforms via query params — e.g. ?w=400&fit

• list_images

  List images in your PixelVault project, most recent first, optionally filtered by custom metadata or AI tag, or searched by AI description (q: alt text, caption, OCR text, best match first). Maps to GET /v1/images with pagination. Requires a PixelVault API key sent as a Bearer to

• get_usage

  Show your plan, this month's usage (storage, uploads) and what is left of the quota, so you can check before a bulk upload. Maps to GET /v1/usage. Read-only. Requires a PixelVault API key sent as a Bearer token in the Authorization header.

• delete_image

  Permanently delete one PixelVault image by id. Maps to DELETE /v1/images/:id. Requires a PixelVault API key sent as a Bearer token in the Authorization header.

• update_image_metadata

  Replace one image's custom metadata (a JSON object you can later filter list_images by). The object replaces the stored one, so send every key to keep; null clears it. Maps to PATCH /v1/images/:id. Requires a PixelVault API key sent as a Bearer token in the Authorization header.

• list_image_tags

  List the AI tags on your described images with how many images carry each, most used first (at most 40). Pass one to list_images (tag) to see those images. Maps to GET /v1/images/tags. Read-only. Requires a PixelVault API key sent as a Bearer token in the Authorization header.

• describe_image

  Start the AI description (alt text, caption, OCR text, up to 6 tags) of an image you already uploaded without describe=true. Idempotent: an image that is already described or in progress returns its state and uses none of your allowance. It takes a few seconds: call get_image unt

• create_upload_url

  Prepare a public image upload from a local shell file when no host attachment download URL exists. Compute the file size and SHA-256 in the shell, then call this tool with filename, size and sha256. Returns a 10-minute URL and curl command to PUT the raw file bytes without an API

• upload_image

  Upload an image publicly to PixelVault and get an instant CDN URL. Maps to POST /v1/images. Provide exactly one of `file` (a host-provided attachment), `source_url` (a public http(s) URL the server fetches), or `data` (base64-encoded bytes). Prefer file for attachments; optional

• upload_batch

  Upload many images (1–50) in one call, grouped into a collection — e.g. a CI run or a set of generated variants. Maps to POST /v1/images/batch. Each item is `data` (base64) or `source_url` (server-fetched, SSRF-guarded), with optional `filename`/`metadata`. Set `visibility: "priv

• list_collections

  List your project's collections (CI runs, generation sets, albums — what upload_batch creates), newest first. Maps to GET /v1/collections. Optional `type` and `name` filters (name is the CI run id, generation id, etc.) and pagination. Requires a PixelVault API key sent as a Beare

• get_collection

  Get one collection and its images by id. Maps to GET /v1/collections/:id. Each image has a `visibility`: for `private` images the returned URL is the plain CDN URL, which returns 403 without a signature, so call sign_url with the image id for a viewable link (a signed URL cannot

• close_collection

  Close a collection (e.g. when a PR merges). Maps to POST /v1/collections/:id/close. Call get_collection first and check its `type`: for `ci_build` collections closing makes every image in it eligible for deletion, which a background sweep (hourly, in batches) then carries out per

• sign_url

  Mint a time-limited signed URL for a private image. Maps to POST /v1/images/:id/sign-url. Provide `id` and optional `expires_in` (seconds, default 3600). The signature binds the image, so the URL can't be replayed against another image; strip it and the CDN returns 403. Deleting

• transform_image

  Build an on-the-fly transform URL for a PixelVault image (resize, crop, format/quality, AI background removal, blur/sharpen/rotate/flip, brightness/contrast/saturation, and same-project watermark tiling). Provide exactly one of `url` (a PixelVault CDN URL) or `id` (an image id, r

• rescue_imgur

  Scan a web page for hotlinked Imgur images and return a PixelVault rescue URL for each — a proxy that lazily rehosts the image on first request, keeping it working through the UK Imgur block. The anonymous rescue tier is a durable ~30-day edge cache (see `cache_ttl_days` in the r

• generate_image

  Generate an image from a text prompt with a Cloudflare Workers AI model and host it on PixelVault in one call; returns the permanent CDN URL. Maps to POST /v1/images/generate. Spends credits from the monthly grant (free 10, Starter 300, Pro 1500; resets on the 1st, UTC): flux-1-s

• upgrade_plan

  Start a paid-plan checkout (`starter` or `pro`). Maps to POST /v1/billing/checkout. Returns a Stripe Checkout URL — it does NOT charge anything: the account owner must open the URL and pay, so show it only to them. The plan changes only after Stripe confirms, so call get_usage af

• manage_billing

  Open the Stripe billing portal to change plan, update payment details or cancel. Maps to POST /v1/billing/portal. Returns a URL for the account owner to open; nothing changes until they act there. The URL can cancel the subscription and change payment details, so show it only to

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7日

• ! 注意

  作者与仓库一致

  发布者（pixelvault-dev）不是仓库所有者（pixelvault-dev）；可能是其他人代为上架的

• … 尚未检查

  仍在维护

  我们还没有从 GitHub 读取这个仓库

• … 尚未检查

  有许可证

  我们还没有从 GitHub 读取这个仓库

• ✓ 通过

  端点有响应

  在 142 毫秒内响应（HTTP 200）

• – 不适用

  使用 OAuth 登录

  无需登录

• ✓ 通过

  工具描述中没有隐藏指令

  已读取 19 个工具描述，未发现针对 AI 的隐藏指令

与“设计、图片与音频”中的其他服务器比较i

• 星标数多于此分类中其他 2204 个服务器的 0%
• 发布到注册中心的时间比此分类中其他 2204 个服务器的 70% 更新
• 基础检查结果等于或优于此分类中其他 2204 个服务器的 43%

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。

替代选择

同一分类中其他作者的服务器，按星标数排序。

如何看卡片：★ 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

作者的 README

仓库中没有找到 README