dentro

Name: dentro
Author: dentro-fyi

Local

dentro.fyiBusiness & Marketing0Updated 26w ago

Repository Visit website

About dentro

dentro provides MCP-compatible agents with structured commerce data for a curated registry of DTC brands across 16 countries. Its tools support brand discovery and product lookup with prices, stock, variants, and other details.

Key features

01Discover DTC brands by natural-language query
02Search products within a brand
03Retrieve product details and variants
04Browse brand category trees
05Get brand metadata and agent instructions

Use cases

01Find brands matching a product description
02Compare product prices and stock within a brand
03Explore a brand’s categories and product variants

MCP support

The MCP server exposes five tools for discovering brands and querying their product, category, and site information. Results are returned as structured JSON for MCP-compatible agents.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config

{
  "mcpServers": {
    "dentro-fyi-dentro": {
      "command": "npx",
      "args": [
        "-y",
        "@dentro-fyi/mcp"
      ],
      "env": {
        "DENTRO_API_KEY": "<DENTRO_API_KEY>"
      }
    }
  }
}

Run commandnpx -y @dentro-fyi/mcp

Environment variables to set

DENTRO_API_KEYSecretAPI key from dentro.fyi (free tier available)

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages

npm@dentro-fyi/mcp0.1.1stdio

Tools

Saved tool list · updated 2w ago

Parameter	Type	Required	Description
limit	number	No	Max results (1-50). Default 10.
query	string	Yes	Natural-language description of what you are looking for (e.g. "sustainable tote bags", "merino wool socks for men")
category	string	No	Optional category filter (e.g. "apparel", "footwear")

Details

From the project README

dentro MCP

Structured commerce data for AI agents. One MCP server, 22,000+ DTC brands, real-time product data, no scraping, no hallucination.

What it does

Lets any MCP-compatible agent (Claude Desktop, Cursor, custom agents) query a curated registry of 22,000+ DTC e-commerce brands across 16 countries. Five tools, all returning clean JSON:

discover_companies — find brands by natural-language query
search_products — search products within a brand, real prices and stock
get_product — full product detail with variants, images, descriptions
list_categories — browse a brand's category tree
get_site_info — brand metadata and agent instructions

Why use it

Without dentro	With dentro
Agent web-searches Google, scrapes 10 storefronts, hallucinates prices	One tool call, structured JSON, real data
30+ second latency, 50K+ tokens	Sub-second, ~2K tokens
Generic results dominated by Amazon	Curated DTC brands, agent-optimized

Install

npm install -g @dentro-fyi/mcp

Get an API key at dentro.fyi (free tier available).

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "dentro": {
      "command": "npx",
      "args": ["-y", "@dentro-fyi/mcp"],
      "env": {
        "DENTRO_API_KEY": "your-key-here"
      }
    }
  }
}

Restart Claude Desktop. Try: "Find me a sustainable tote bag under $30."

Cursor / other MCP clients

Same config shape. Any MCP-compatible client can use it.

Example

You: I need merino wool socks for hiking, ideally American-made.
Claude: [calls discover_companies({query: "merino wool hiking socks American-made"})]
        [finds: Darn Tough, Smartwool, Farm to Feet]
        [calls search_products({company_id: "darn-tough", query: "merino hiking"})]
        Here are 3 options from Darn Tough, all in stock, made in Vermont...

Coverage

22,173 brands across 16 countries
4 verified platforms (Shopify, WooCommerce, WordPress, Magento) plus custom connectors
Tier 1 (verified): full product API
Tier 2 (listed): structured data only
Tier 3 (directory): brand info only

Pricing

Free tier: 100 requests/day, all tools
Paid tiers: higher limits, priority discovery, attribution analytics
See dentro.fyi/pricing

Resources

Docs: dentro.fyi/docs
API reference: dentro.fyi/api
Issues: github.com/dentro-fyi/dentro-mcp/issues
Contact: [email protected]

License

MIT.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

Read the getting-started guide

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.