mcpField
T
TinyPNG MCP by usefulapi

TinyPNG MCP by usefulapi

Remote
usefulapi.ioMedia & Design0Updated today

About TinyPNG MCP by usefulapi

TinyPNG MCP by usefulapi is a hosted MCP server for image operations through TinyPNG. It compresses images from URLs, can resize or convert the compressed result, and reports monthly compression usage.

Key features

  1. 01Compress images from URLs
  2. 02Resize compressed images
  3. 03Convert to WebP, AVIF, PNG or JPEG
  4. 04Download compressed images
  5. 05Check monthly compression usage

Use cases

  1. 01Compress an image available at a URL
  2. 02Resize or convert a compressed image
  3. 03Check compression use for the month

MCP support

Exposes TinyPNG image-compression, transformation, download and usage tools to MCP clients through a hosted remote MCP server. Authentication uses OAuth with the user's TinyPNG credentials.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://tinypng.usefulapi.io/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

4
ParameterTypeRequiredDescription
urlstringYesPublic http(s) URL of the image to compress. Tinify's servers fetch it, so it must be reachable from the internet.

Details

From the project README

TinyPNG MCP by usefulapi

Use TinyPNG from Claude, Cursor, or any MCP client — compress an image by URL, resize or convert the result (WebP, AVIF, PNG, JPEG), download it, and check how many compressions your key used this month. Hosted, no local install: connect with your own TinyPNG credentials.

Live endpoint: https://tinypng.usefulapi.io/mcp · Homepage: https://usefulapi.io/tinypng

Connect

  • Claude (claude.ai, Desktop): open Customize → Connectors, click + Add → Add custom connector, and paste https://tinypng.usefulapi.io/mcp.
  • Claude Code: claude mcp add --transport http tinypng https://tinypng.usefulapi.io/mcp, then run /mcp to log in.
  • VS Code: Add to VS Code.
  • Cursor and other clients: add the URL as a remote MCP server:
{
  "mcpServers": {
    "tinypng": {
      "url": "https://tinypng.usefulapi.io/mcp"
    }
  }
}

Add only the URL. Do not add an Authorization header or an API key to the client config: the server signs you in with OAuth, and the login page asks for your TinyPNG credentials.

Step-by-step setup, where to find your credentials, and FAQ: https://usefulapi.io/tinypng/

Tools

ToolTypeWhat it does
tinypng_compress_imagewriteCompress an image from a URL
tinypng_transform_imagewriteResize, convert or keep metadata of a compressed image
tinypng_download_imagereadDownload a compressed image
tinypng_get_usagereadGet compression usage this month
tinypng_usage_statusmetaUsage status (free-tier meter)
tinypng_request_featuremetaRequest a missing feature
tinypng_upgrademetaUpgrade to Pro (unlimited*)
tinypng_cancel_subscriptionmetaCancel the Pro subscription

read tools are read-only; write tools mutate data (clients should confirm them); meta tools report usage, manage your subscription or send a feature request.

Pricing

PlanPriceLimit
Free$050 tool calls / month
Pro (per API key)$9/mo or $90/yr (2 months free)Unlimited*

*Pro has a fair use limit of 10,000 tool calls a month on this server. For more, write to [email protected].

Pro covers this server only. Subscribe with tinypng_upgrade (it returns a Stripe Checkout link). Cancel any time with tinypng_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running tinypng_upgrade before then undoes the cancel. Or write to [email protected].

License

MIT © usefulapi. Not affiliated with or endorsed by TinyPNG.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.