Skip to content
BrandReel logo

BrandReel MCP server

Which MCP servers are BrandReel's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-09

← Back to BrandReel

Whose server it is
  • Addresshttps://brandreel.com/api/mcpnot in the official registry: answered when asked

No entry in the official MCP registry names this server. It answered on brandreel.com when the Atlas asked at the address servers are usually mounted on, so it is the vendor's own. Clients and catalogues that list servers from the registry do not show it.

When we asked itchecked 2026-10-28
  • Stateanswerschecked 2026-10-28
  • Tools13
  • Server calls itselfbrandreel
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 856 ms.

Should an agent connect itConnect it, with care
  • Its tools do every use case we checked: Generate product ads and social reels from brand assets; Create cinematic brand videos in minutes from text prompts; Produce vertical videos for Instagram, TikTok and YouTube.

Once connected

  • For "Generate product ads and social reels from brand assets", the likely first call is get_usage.
  • For "Create cinematic brand videos in minutes from text prompts", the likely first call is get_usage.
  • For "Produce vertical videos for Instagram, TikTok and YouTube", the likely first call is get_usage.
  • create_brand, create_generation_record change data without a sign-in: anyone with the address can call them.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 8, the first on 2026-10-28
  • INITE MCP score79 of 100answers 100 · does the job 100 · definitions 96 · context 100 · connects 100 · lowered by the warning signs below
  • What an agent can do with it3 of 3 use cases
  • Answered100% of days8 of 8 daily checks
  • Median first answer793 ms
  • Space in an agent's context≈ 1,584 tokensthe definitions of all its tools (13), which an agent carries on every turn
  • Tool definitionsA · 96 of 100
  • Typed results0 of 13 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 3 of 13

What an agent can do with it

  • can do · Generate product ads and social reels from brand assets
  • can do · Create cinematic brand videos in minutes from text prompts
  • can do · Produce vertical videos for Instagram, TikTok and YouTube

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

  • Tools that change data, on a server that answers without a sign-in: create_brand, create_generation_record

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers13 tools · read 2026-10-28
  • get_usage

    Available, reserved, purchased, and lifetime-used generation credits. Call before any generation.

  • list_models

    Live image and video model capabilities, supported options, defaults, and credit costs.

  • list_brands

    All brand workspaces owned by the API-key account.

  • create_brand

    Create an owned brand workspace. Confirm the name and context with the user first.

  • get_brand

    One owned workspace with its logo, palette, tagline, website, and asset references.

  • list_brand_assets

    Resolve the owned workspace logo and reusable visual assets to fresh URLs.

  • list_generations

    Recent image and video generations for a brand. Use this to avoid duplicates.

  • get_generation

    Status, media URL, prompt, settings, and provider jobs for one owned generation.

  • create_generation_record

    Create the owned record required before starting image or video generation. This does not spend credits by itself.

  • start_image_generation

    Spend credits to start an approved image generation. Read usage/models/assets first and set maxCredits.

  • start_video_generation

    Spend credits to start an approved video generation. Read usage/models/assets first and set maxCredits.

  • start_video_upscale

    Spend credits to finish an owned completed video with BytePlus Video Enhancement Pro. The source remains available while the job runs.

  • get_video_status

    Poll an existing video job instead of creating a duplicate.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "brandreel": {
      "type": "http",
      "url": "https://brandreel.com/api/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http brandreel https://brandreel.com/api/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://brandreel.com/api/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.