LLPRO Campus

Remove the background from one photo (transparent PNG, signed)

photo_background_remove

Idempotent

Remove the background from ONE photo. Send the public https/http address of a JPEG, PNG or WebP photo (10 MB at most, one photo per call, no lists); get back the same photo as a PNG with a soft transparent background (image_png_base64), the share of the picture that was kept, plain warnings when the cut looks doubtful, and a signed, dated record tying the result to the photo it came from. Free, no sign-up, 20 photos a day per caller. The result is returned in the answer and kept nowhere: save it yourself. The longest side of the result is at most 1600 px. Runs an open-weights segmentation model (BiRefNet, MIT licence) on LLPRO's own image worker. Public addresses only (ports 80 and 443); metadata (EXIF, location) is not carried into the result. It makes no promise that the cut is perfect: hair, glass, shadows and cluttered scenes can be wrong; look at the picture before you use it. For a listing, pass the result on to the Seller Agent (https://llpro.ai/seller-agent).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "image_url": "<image_url>"
    },
    "name": "photo_background_remove"
  }
}

Input Schema

Name	Required	Description	Default
`image_url`	Yes	Public http(s) address of ONE JPEG, PNG or WebP photo, up to 10 MB.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 13, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=true, destructiveHint=false) by disclosing the free tier of 20 photos/day per caller, that nothing is stored server-side, the 1600 px output cap, EXIF/location stripping, and the BiRefNet model behind the segmentation. It also honestly flags the quality failure modes (hair, glass, shadows, cluttered scenes) and warns the caller to inspect before use — exactly the caveats an agent needs before acting on the result.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the verb, resource and output type in the first sentence, then packs limits, output fields, retention and caveats into a single dense paragraph. It is long for one parameter, but nearly every clause carries operational weight; only the format/size restatement duplicates the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description names the return fields (image_png_base64, retained-share metric, warnings, signed dated record) and covers retention, rate limits, resolution cap and accuracy limits. An agent can decide, call and correctly interpret the result without opening anything else.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for the single image_url parameter, so the baseline is 3; the description still adds meaning the schema lacks, namely that only ports 80 and 443 are accepted and that URL lists are rejected. It restates the 10 MB and format limits, which is redundant but harmless.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (remove background from ONE photo) plus the exact output artifact: a transparent PNG returned as image_png_base64. The 'ONE photo, no lists' scoping and the signed record of provenance distinguish it from a generic batch image tool at a glance.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear operating context: one photo per call, public http(s) URL on ports 80/443, JPEG/PNG/WebP up to 10 MB, and a downstream hand-off to the Seller Agent for listings. It does not name an alternative tool to use when the input is already a base64 blob or an unpublishable local file, so the exclusion side is only partly covered.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All LLPRO Campus tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?