PluginBench
MCP Server
Active
MIT

Brandfetch MCP Server

io.brandfetch/brandfetch

Search brands and retrieve logos, company data, and design assets from Brandfetch's API.

What is the Brandfetch MCP server?

The Brandfetch MCP server gives AI assistants access to brand search, company data, logos, design assets, and LLM-ready brand context from the Brandfetch API. It enables lookups by domain, email, ticker, ISIN, or crypto symbol, and can identify merchants from transaction strings. The server supports interactive brand cards on compatible hosts and includes tools for logo URL construction and brand enrichment.

Brandfetch MCP provides AI agents with comprehensive brand intelligence: search for brands, retrieve logos and design assets, look up company data, enrich transactions with merchant information, and get LLM-ready brand context including voice, audience, and positioning. Use it to build brand-aware applications, populate logo walls, identify merchants from payment data, or generate brand-informed content.

How to install Brandfetch

Copy-paste configuration for popular MCP clients.

transport: http
Config generated by PluginBench — verify against the source before use.
~/.cursor/mcp.json
{
  "mcpServers": {
    "brandfetch": {
      "url": "https://mcp.brandfetch.io/mcp"
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

  • brand_search — Search for brands by name using Brandfetch's search index.
  • get_brand — Look up full brand data by domain, email, ticker, ISIN, or crypto symbol; renders an interactive brand card on compatible hosts.
  • get_brand_data — Retrieve the same brand data without a card—for logo walls, multi-brand work, and data feeding generated content.
  • enrich_transaction — Identify a merchant brand from a credit-card or bank-statement string.
  • get_brand_context — Get LLM-ready brand context for a domain including voice, audience, positioning, and style.
  • build_logo_urls — Construct Brandfetch Logo CDN URLs for one or more brands without making an API call.
  • send_feedback — Report bugs, wrong or stale brand data, or missing capabilities to Brandfetch.

Use cases

  • Search for brands and retrieve their logos, colors, fonts, and design assets for brand-aware applications
  • Look up company data and brand context by domain, email, ticker symbol, or crypto address
  • Identify merchants and brands from credit-card or bank-statement transaction strings for transaction enrichment
  • Build logo walls or multi-brand galleries with efficient data retrieval
  • Generate brand-informed content using LLM-ready brand context including voice, audience, and positioning

Brandfetch MCP server FAQ

What is the Brandfetch MCP server?

It's an official MCP server that connects AI assistants to Brandfetch's brand intelligence API, providing brand search, company data, logos, design assets, and LLM-ready brand context.

Is Brandfetch free to use?

The hosted server requires a Brandfetch account and API token. Some tools like brand_search and build_logo_urls don't consume credits, but get_brand, get_brand_data, enrich_transaction, and get_brand_context do. Check the Brandfetch dashboard for pricing and usage.

How do I install it in Claude Desktop?

Add the server to your Claude Desktop config with type 'http', URL 'https://mcp.brandfetch.io/mcp', and an Authorization header with your Brandfetch token (bf1.YOUR_TOKEN).

How do I install it in Cursor?

Add the server to ~/.cursor/mcp.json with the URL 'https://mcp.brandfetch.io/mcp' and an Authorization header containing your Brandfetch bearer token.

Do I need authentication?

Yes. Generate a Brandfetch MCP token (bf1. bearer token) from the Keys and MCP page in the Brandfetch dashboard, or use OAuth if your client supports it.

Can I self-host this server?

Yes. The server is built with FastMCP and can be self-hosted using Docker or by running uvicorn directly with Python 3.11+.

README (reference)

Source of truth, from the repository.

Brandfetch MCP Server

The official Model Context Protocol server for Brandfetch. It gives AI assistants access to brand search, company data, logos and design assets, and LLM-ready brand context from the Brandfetch API.

Tools

ToolDescription
brand_searchSearch for brands by name using Brandfetch's search index.
get_brandLook up full brand data by domain, email, ticker, ISIN, or crypto symbol; renders the interactive brand card on MCP Apps hosts.
get_brand_dataThe same brand data with no card — for logo walls, multi-brand work, and data that feeds generated content.
enrich_transactionIdentify a merchant brand from a credit-card or bank-statement string.
get_brand_contextGet LLM-ready brand context for a domain — voice, audience, positioning, style.
build_logo_urlsConstruct Brandfetch Logo CDN URLs for one or more brands (no API call).
send_feedbackReport bugs, wrong or stale brand data, or missing capabilities to Brandfetch.

Interactive brand card (MCP Apps)

On hosts that support the MCP Apps extension (claude.ai, Claude Desktop, ...), get_brand results render as an interactive brand card: logo preview, format switcher (SVG/PNG/WebP/...), download and copy-URL actions. Hosts without Apps support fall back to the regular JSON tool result. get_brand_data returns the same brand data without the card, so a logo wall of six brands is six data calls rather than six cards; the model picks between the two by their descriptions. The widget source lives in ui/ and is served by the server as the ui://brandfetch/brand-card.html resource.

Quick start (hosted server)

The easiest way to use this server is to connect to the Brandfetch-hosted endpoint — no install, no infrastructure:

https://mcp.brandfetch.io/mcp

Authentication uses a Brandfetch MCP token (a bf1. bearer token). Generate one from the Keys and MCP page in the Brandfetch dashboard, or connect via OAuth from a client that supports it.

Claude Desktop / Claude Code

{
  "mcpServers": {
    "brandfetch": {
      "type": "http",
      "url": "https://mcp.brandfetch.io/mcp",
      "headers": {
        "Authorization": "Bearer bf1.YOUR_TOKEN"
      }
    }
  }
}

Cursor

Add to ~/.cursor/mcp.json (or the project .cursor/mcp.json):

{
  "mcpServers": {
    "brandfetch": {
      "url": "https://mcp.brandfetch.io/mcp",
      "headers": {
        "Authorization": "Bearer bf1.YOUR_TOKEN"
      }
    }
  }
}

Clients that support OAuth can instead point at https://mcp.brandfetch.io/mcp with no token and complete the authorization flow in the browser.

Quota errors

get_brand, get_brand_data, enrich_transaction, and get_brand_context consume API credits from your plan; brand_search and build_logo_urls don't and keep working when your credits run out.

  • 429 "API quota exhausted" — your key has used all of its API credits. Check usage or upgrade in the Brandfetch dashboard.
  • 403 "Forbidden" — the key has no available API credits or lacks access to that endpoint. The key itself may be valid, so check your plan and key status in the dashboard before rotating it.

Self-hosting

This is an HTTP (streamable-http) MCP server built with FastMCP. You can run your own instance with Docker.

docker build -t brandfetch-mcp-server .
docker run --rm -p 8080:8080 brandfetch-mcp-server

The server then listens on http://localhost:8080/mcp. Point your MCP client at that URL and send your Brandfetch credentials as a Bearer token.

The Dockerfile bundles the AWS Lambda Web Adapter and a few AWS_LWA_* environment variables. These are inert outside of AWS Lambda and can be ignored (or removed) for a plain container/host deployment.

Running without Docker

uv sync
uv run uvicorn src.main:app --host 0.0.0.0 --port 8080

Development

Requires uv and Python 3.11.

uv sync                 # install dependencies
uv run pytest           # run the tests
uv run ruff check .     # lint
uv run ruff format .    # format

License

MIT

Related MCP servers

Coding agents read frozen requirements, report progress, and submit delivery evidence.

Convert any image into machine embroidery files (DST, PES…) or vector graphics (SVG, PDF, EPS, DXF).

Orchestration & technical-consulting MCP for end-to-end Salesforce, ServiceNow & HubSpot back-end.

0
View repository →

Social listening for AI agents: search mentions, pull scored buying signals, score leads

MCP server for Calvix Technology Solutions — query IT services, contact info, and company details.

Run B2B outreach from your AI agent: 250+ tools for campaigns, leads, LinkedIn and email workflows.