Mcp Brand Sponsor Finder

Brand Sponsor Finder MCP Server

[Glama score] [MCP Registry] [npm version] [npm downloads] [license] [mcpservers.org]

[Brand Sponsor Finder MCP server]

Find the brands that paid creators in a niche in the last 90 days, with the public evidence for each placement. One row per brand with a recency score, and one row per sighting with its evidence link, date, and promo code.

What's Inside

• What it does
• Quick start
• Prerequisites
• Example prompts
• Tool
• Inputs
• Pricing
• Your keys
• Full actor documentation
• License

What it does

• Reads public YouTube video descriptions (channel feeds, or your own YouTube Data API key), podcast show notes, newsletter issues, and event sponsor pages for sponsor lines, promo codes, and sponsor slots.
• Follows shortlinks and affiliate redirects to the brand's own domain, and merges every sighting into one row per brand domain.
• Checks the brands it found for open partnership job posts (Greenhouse, Lever, Ashby) and creator or affiliate program pages, which become the brand's public contact.
• Returns only sightings inside your date window, each with an evidence link. Instagram, TikTok, and the Meta Ad Library are not read.

All of the work runs on Apify. This package is a thin client that starts the actor run, waits for it, and hands back the dataset rows.

Row cap and paging

One run can return hundreds of rows (633 rows and about 0.8 MB of text on a 30 day health and fitness search), which is more than an agent context holds. So each call returns at most max_rows rows: 50 unless you set it, and never more than 200.

1. The first call starts the run and returns the first page. The first content block is the JSON array of rows. The second is a paging block with run_id, total_rows, rows_returned, and next_cursor.
2. To get the next page, call find_brand_sponsors again with only cursor set to next_cursor. Add max_rows to change the page size.
3. Repeat until next_cursor is null.

A cursor call starts no run. It reads the next page of rows the first run already wrote, so no row is billed twice. A cursor works for as long as Apify keeps that run's dataset.

Quick start

You need Node.js 18 or newer and an Apify account with an API token.

Add this to your Claude Desktop config (claude_desktop_config.json), Cursor, or any MCP client:

{  "mcpServers": {    "mamba-brand-sponsor-finder": {      "command": "npx",      "args": [        "-y",        "@mambalabsdev/mcp-brand-sponsor-finder"      ],      "env": {        "APIFY_TOKEN": "your-apify-token"      }    }  }}

Restart the client. The find_brand_sponsors tool appears.

Prerequisites

• Node.js 18 or newer.
• An Apify API token from console.apify.com/account/integrations, set as APIFY_TOKEN. The server lists its tool without a token; a call needs one.

Example prompts

• "Find brands sponsoring health and fitness creators in the last 90 days."
• "Which brands paid beauty YouTubers this month? Brand rows only."
• "List coffee brands sponsoring podcasts and newsletters, with promo codes."

Tool

find_brand_sponsors. One tool. Example arguments:

{  "niche": "health and fitness",  "window_days": "90"}

Inputs

Every buyer facing input of the actor, unchanged, plus the two paging settings. Omitted inputs take the actor's own defaults. Numbers and booleans are sent as strings.

Pricing

Pay per event on Apify, billed to your Apify account. Prices in USD.

Free rows: a run with no result writes one free row that says why, and a refused input writes one free row whose error_reason starts with input_invalid:.

Your keys

No key is needed. Your own YouTube Data API key is optional: set YOUTUBE_API_KEY in this server's environment and it is passed to the actor as youtube_api_key, so the key never goes through the conversation. With it the actor searches YouTube for channels in the niche and reads up to 50 uploads per channel.

Full actor documentation

apify.com/mambalabs/brand-sponsor-finder

License

MIT. See LICENSE.