Skip to main content
Glama

Remove Background

sirv_remove_background

Remove the background from an image and return a transparent PNG for product cut-outs; the result is saved as a new studio asset while the source image stays unchanged.

Instructions

Remove the background from one image and return a PNG with a transparent background.

Use it for product cut-outs. Do not use it to put the subject on a new background: sirv_replace_background does that in one step.

Inputs: image_url is required. provider picks the service (default birefnet). model and operating_resolution tune birefnet only; bria and pixelcut ignore them.

Studio also saves the result in the library as a new asset. The source image does not change. Returns result_url, the URL of the PNG.

Credits: spends workspace credits. The cost depends on the model and options.

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": "sirv_remove_background"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNoBiRefNet model. Matting suits hair and fur; Portrait suits people. Default: General Use (Heavy)General Use (Heavy)
providerNoService that removes the background: birefnet (fine edges, such as hair), bria (faster) or pixelcut (made for product cut-outs). Default: birefnetbirefnet
image_urlYesPublic URL of the image
operating_resolutionNoBiRefNet working size. A larger size gives finer edges but is slower. Default: 1024x10241024x1024

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.1.1
    • changedInput schema / properties / image_url / description
      Previous value: -"URL of the image to process"New value: +"Public URL of the image"
    • changedInput schema / properties / model / description
      Previous value: -"Model to use for background removal. 'General Use (Heavy)' is recommended for best quality"New value: +"BiRefNet model. Matting suits hair and fur; Portrait suits people. Default: General Use (Heavy)"
    • changedInput schema / properties / operating_resolution / description
      Previous value: -"Processing resolution. Higher = better quality but slower"New value: +"BiRefNet working size. A larger size gives finer edges but is slower. Default: 1024x1024"
    • changedInput schema / properties / provider / description
      Previous value: -"Background removal provider: 'birefnet' (default, best quality), 'bria' (faster) or 'pixelcut' (cleanest product cut-outs)"New value: +"Service that removes the background: birefnet (fine edges, such as hair), bria (faster) or pixelcut (made for product cut-outs). Default: birefnet"
  2. First observedv0.1.0

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already flag a non-read-only, open-world, non-idempotent, non-destructive call, and the description adds real context beyond them: the result is saved into the library as a new asset, the source image is untouched, credits are spent at a cost that varies by model and options, and the return value is result_url. These are the exact facts an agent needs before invoking a credit-spending mutation.

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

Conciseness5/5

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

Broken into short purpose, routing, inputs, side-effects, and cost blocks with the key constraint front-loaded. No sentence repeats structured data needlessly and nothing is padded.

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?

No output schema exists, yet the description names the return field (result_url) and explains the library side effect, so nothing essential about calling or interpreting the result is missing. Cost note closes the remaining gap for a credit-spending tool.

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%, so the baseline is 3; the description earns more by disclosing a cross-parameter interaction the schema only implies: model and operating_resolution 'tune birefnet only; bria and pixelcut ignore them'. It also restates the provider default, which is already in the schema.

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 the background from one image and return a PNG with a transparent background') and immediately contrasts with the sibling that adds a background. An agent can distinguish this from sirv_replace_background without opening either schema.

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

Usage Guidelines5/5

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

Gives an explicit when-to-use ('product cut-outs') and an explicit when-not-to-use with the named alternative ('Do not use it to put the subject on a new background: sirv_replace_background does that in one step'). Routing is unambiguous.

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