Skip to main content
Glama

bgremover-mcp

Model Context Protocol (MCP) server for BGRemover Video. It lets Claude Desktop, Claude Code, Cursor, and other MCP clients remove or replace the background of videos and images.

MCP client -> bgremover-mcp -> https://www.bgremover.video/api/v1/* -> BGRemover backend

The server only calls the public /api/v1 API. It never touches internal routes, FastAPI/RunPod URLs, S3 buckets, or the database.

Tools

Tool

Endpoint

Notes

remove_video_background

POST /videos/remove-background

Async. Transparent, solid color, or image background.

remove_image_background

POST /images/remove-background

Synchronous, 1 credit.

get_job_status

GET /jobs/{job_id}

queued / processing / completed / failed; output_url when done.

check_credits

GET /me/credits

list_features

GET /features

upload_image, upload_video

POST /uploads/{image,video}

stdio server only (reads local files).

Video credits: ceil(duration_seconds) * 1.5, doubled for watermark-free exports on accounts that have never purchased credits. If duration_seconds is omitted the backend measures the video; it never guesses.

Related MCP server: media-gen-mcp

Use it

Local (stdio)

Create an API key at https://www.bgremover.video/developers, then:

{
  "mcpServers": {
    "bgremover": {
      "command": "npx",
      "args": ["-y", "bgremover-mcp"],
      "env": { "BGREMOVER_API_KEY": "vbr_..." }
    }
  }
}

Remote (HTTP + OAuth)

https://mcp.bgremover.video/mcp accepts either a vbr_ API key as a Bearer token or an OAuth 2.1 token (authorization code + PKCE, dynamic client registration) issued by bgremover.video, so web Claude and ChatGPT can connect without handling keys.

Development

npm install
npm run typecheck
npm test
npm run build
npm run dev          # stdio, needs BGREMOVER_API_KEY
npm run dev:http     # HTTP server on :3000

See .env.example for configuration.

Notes

  • Developer API keys default to 100 calls/day and 1000/month on the website. Every tool call, including get_job_status polling, counts toward that limit.

  • Keys created through the OAuth flow have no call limits and expire after 7 days (refreshed automatically via refresh tokens).

bgremover-mcp

Available Tools

7 tools
check_creditsCheck CreditsA
Read-onlyIdempotent

This tool will check the remaining BGRemover Video credits and account usage information for the calling API key. It takes no arguments.

Inputs: no named parameters.

get_job_statusGet Job StatusA
Read-onlyIdempotent

This tool will fetch the status and result of an asynchronous BGRemover Video job (returned by remove_video_background). Status is one of queued, processing, completed, failed; when completed the response includes output_url. It takes the following argument: - job_id (str, required): The job_id returned by the asynchronous tool call.

Inputs: job_id (required).

list_featuresList FeaturesA
Read-onlyIdempotent

This tool will list every available BGRemover Video tool, its endpoint, input schema, and credit cost. It takes no arguments.

Inputs: no named parameters.

remove_image_backgroundRemove Image BackgroundB
Destructive

This tool will remove or replace the background of an image, returning a transparent, solid-color, or custom-image background. It spends 1 credit. It takes the following arguments: - media_file or image_url (one required): The image to process, either an uploaded file or a public URL. - output_transparent (bool, optional): Make the background transparent. Defaults to true unless a color or image background is given. - background_color (str, optional): Hex color to fill the background with. - background_image_url (str, optional): Public URL of an image to use as the new background.

Inputs: image_url, media_file, background_color, output_transparent, +1 more.

remove_video_backgroundRemove Video BackgroundA
Destructive

This tool will remove or replace the background of a video, producing a transparent, solid-color, or custom-image background. This is an asynchronous operation and spends credits; use get_job_status with the returned job_id to retrieve the result. It takes the following arguments: - media_file or video_url (one required): The video to process, either an uploaded file or a public URL that links directly to a real video file (not a web page). - output_transparent (bool, optional): Make the background transparent. Defaults to true unless a color or image background is given. - background_color (str, optional): Hex color to fill the background with. - background_image_url (str, optional): Public URL of an image to use as the new background. - duration_seconds (number, optional): Informational only; the server measures the real length (max 3600s) to price the job. - is_watermark (bool, optional): Defaults to true. Watermark-free exports cost double for accounts that have never purchased credits.

Inputs: video_url, media_file, is_watermark, background_color, +3 more.

upload_imageUpload ImageA
Destructive

This tool will upload a local image file to BGRemover Video and return a CDN URL that can be passed as image_url or media_url to another BGRemover Video tool. It takes one argument: - file_path (str, required): Absolute local path to the image file.

Inputs: file_path (required).

upload_videoUpload VideoA
Destructive

This tool will upload a local video file to BGRemover Video and return a CDN URL that can be passed as video_url or media_url to another BGRemover Video tool. It takes one argument: - file_path (str, required): Absolute local path to the video file.

Inputs: file_path (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4/5.0

    Scored across 7 tools

    Disambiguation5/5

    Each tool targets a clearly distinct action and resource: uploads are split by media type, background removal is split by media type, and job status is a single-purpose polling tool. The video/image pairs are near-parallel but unambiguously named and scoped, so an agent can select correctly without guessing.

    Naming Consistency5/5

    All seven tools use a consistent snake_case verb_noun pattern (upload_image, check_credits, remove_video_background, get_job_status). No mixed conventions or vague verbs anywhere in the set.

    Tool Count5/5

    Seven tools is well-scoped for a background-removal service: two uploads, two processing operations, one async poller, and two account/introspection utilities. Every tool earns its place with no redundancy.

    Completeness4/5

    The core lifecycle (upload -> process -> poll result) plus credits and feature discovery is covered for both image and video. Minor gaps remain: no job cancellation, no listing of past jobs or uploaded assets, and no cleanup/delete for uploaded files.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers