Brand Sponsor Finder MCP Server
Checks discovered brand domains for open partnership job posts on Greenhouse, using those postings as a public-contact and partnership signal for sponsorship prospecting.
Reads podcast RSS feed URLs as seed sources, extracting sponsor mentions, promo codes, and evidence from episode show notes and descriptions.
Reads public YouTube video descriptions and channel feeds to find sponsor lines, promo codes, and sponsor placements, with optional use of a YouTube Data API key for additional channel search.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Brand Sponsor Finder MCP Serverfind brands sponsoring fitness creators in the last 90 days"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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
Related MCP server: @aryaminus/socials-mcp
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.
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. Omitted inputs take the actor's own defaults. Numbers and booleans are sent as strings.
Input | Type | Description |
| string | The audience niche, for example "health and fitness", "beauty and skincare", or "food and beverage". Searches for channels, shows, and newsletters use it, and every row carries it. These three niches also start from a list of sources Mamba Labs has read before (turn off with use_niche_presets) |
| string | Optional. More search terms for the audience, one per line or separated by commas, for example "strength training". Each one widens the podcast, newsletter, and (with your key) YouTube channel search. Up to 20. A text field, so a Clay column maps straight in |
| string | Only sightings from the last N days. Whole number, default 90, at most 365. Sent as text so Clay works Default 90 |
| string | Optional. Which sources to run, separated by commas, any of: youtube, podcast, event, newsletter, job_post, program. Empty runs all of them. job_post and program check the brands the other sources found |
| string | Optional. YouTube channel URLs or @handles, podcast RSS feed URLs, or newsletter URLs to read first, one per line or separated by commas. Each is read even beyond the per source limits |
| string | Optional. Events whose sponsor or partner page to read, as a JSON list of objects: [{"name": "...", "url": "sponsor page URL", "date": "YYYY-MM-DD", "city": "...", "audience": "...", "size": "..."}], or one sponsor page URL per line. url is needed; the rest is optional. A dated event inside the window gives dated rows; an undated or upcoming event gives undated rows |
| string | true or false, default true. For health and fitness, beauty and skincare, and food and beverage, also read the channels, shows, newsletters, and event pages Mamba Labs has read before Default true |
| string | true or false, default true. One row per brand domain with sighting count, last seen date, sources, creators or events, contact, and recency score Default true |
| string | true or false, default true. One row per sighting with its evidence link, date, promo code, placement type, and pitch angle Default true |
| string | YouTube channels read per run. Whole number, default 20, at most 100. Sent as text so Clay works Default 20 |
| string | Newest uploads read per channel (the public feed holds 15). Whole number, default 15, at most 50. Sent as text so Clay works Default 15 |
| string | Podcast shows read per run. Whole number, default 15, at most 100. Sent as text so Clay works Default 15 |
| string | Newest episodes read per show. Whole number, default 8, at most 30. Sent as text so Clay works Default 8 |
| string | Newsletters read per run. Whole number, default 8, at most 50. Sent as text so Clay works Default 8 |
| string | Newest issues read per newsletter. Whole number, default 8, at most 30. Sent as text so Clay works Default 8 |
| string | Brands, most sighted first, whose job boards and program pages are checked. Whole number, default 25, at most 200. Sent as text so Clay works Default 25 |
| string | Optional. The run stops before it would charge more than this |
Pricing
Pay per event on Apify, billed to your Apify account. Prices in USD.
Event | Free plan | Bronze | Silver | Gold |
| $0.02 | $0.019 | $0.018 | $0.017 |
| $0.005 | $0.00475 | $0.0045 | $0.00425 |
| $0.002 | $0.002 | $0.002 | $0.002 |
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.
Available Tools
1 toolfind_brand_sponsorsFind brands paying creators in a niche, with evidenceARead-only
Find brands with recent public proof of paid placement in a niche. Give a niche (for example health and fitness, beauty and skincare, food and beverage) and optionally audience keywords, seed YouTube channels, podcast feeds, or newsletters, and event sponsor pages. The actor reads public YouTube descriptions, podcast show notes, newsletter issues, event sponsor pages, partnership job posts, and brand creator program pages, and returns one row per brand domain (sighting count, last seen date, sources, creators or events sponsored, public contact, recency score) and one row per sighting (brand, domain, source, creator or event, date, evidence link, promo code, placement type, pitch angle). Instagram, TikTok, and the Meta Ad Library are not read. Input with nothing to run returns one free row whose error_reason starts with input_invalid:. A run that does not succeed is returned as an error with its run ID. Read-only; requires an APIFY_TOKEN; Apify charges per brand row, per sighting row, and per run start.
| Name | Required | Description | Default |
|---|---|---|---|
| niche | No | The audience niche, for example "health and fitness", "beauty and skincare", or "food and beverage". Searches for channels, shows, and newsletters use it, and every row carries it. These three niches also start from a list of sources Mamba Labs has read before (turn off with use_niche_presets). | |
| sources | No | Optional. Which sources to run, separated by commas, any of: youtube, podcast, event, newsletter, job_post, program. Empty runs all of them. job_post and program check the brands the other sources found. | |
| window_days | No | Only sightings from the last N days. Whole number, default 90, at most 365. Sent as text so Clay works. Default 90. | |
| max_channels | No | YouTube channels read per run. Whole number, default 20, at most 100. Sent as text so Clay works. Default 20. | |
| max_podcasts | No | Podcast shows read per run. Whole number, default 15, at most 100. Sent as text so Clay works. Default 15. | |
| seed_sources | No | Optional. YouTube channel URLs or @handles, podcast RSS feed URLs, or newsletter URLs to read first, one per line or separated by commas. Each is read even beyond the per source limits. | |
| event_calendar | No | Optional. Events whose sponsor or partner page to read, as a JSON list of objects: [{"name": "...", "url": "sponsor page URL", "date": "YYYY-MM-DD", "city": "...", "audience": "...", "size": "..."}], or one sponsor page URL per line. url is needed; the rest is optional. A dated event inside the window gives dated rows; an undated or upcoming event gives undated rows. | |
| include_brands | No | true or false, default true. One row per brand domain with sighting count, last seen date, sources, creators or events, contact, and recency score. Default true. | |
| max_charge_usd | No | Optional. The run stops before it would charge more than this. | |
| max_newsletters | No | Newsletters read per run. Whole number, default 8, at most 50. Sent as text so Clay works. Default 8. | |
| audience_keywords | No | Optional. More search terms for the audience, one per line or separated by commas, for example "strength training". Each one widens the podcast, newsletter, and (with your key) YouTube channel search. Up to 20. A text field, so a Clay column maps straight in. | |
| include_sightings | No | true or false, default true. One row per sighting with its evidence link, date, promo code, placement type, and pitch angle. Default true. | |
| use_niche_presets | No | true or false, default true. For health and fitness, beauty and skincare, and food and beverage, also read the channels, shows, newsletters, and event pages Mamba Labs has read before. Default true. | |
| max_brands_to_check | No | Brands, most sighted first, whose job boards and program pages are checked. Whole number, default 25, at most 200. Sent as text so Clay works. Default 25. | |
| max_videos_per_channel | No | Newest uploads read per channel (the public feed holds 15). Whole number, default 15, at most 50. Sent as text so Clay works. Default 15. | |
| max_episodes_per_podcast | No | Newest episodes read per show. Whole number, default 8, at most 30. Sent as text so Clay works. Default 8. | |
| max_issues_per_newsletter | No | Newest issues read per newsletter. Whole number, default 8, at most 30. Sent as text so Clay works. Default 8. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Goes well beyond the annotations: it discloses the billing units (per brand row, per sighting row, per run start), the APIFY_TOKEN requirement, the free single-row response for invalid input, and that failures return an error with a run ID. The read-only annotation is consistent and the description adds operational context the annotations cannot carry.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Despite its length, every sentence carries a distinct payload: purpose, inputs, return shape, exclusions, error behavior, and cost, roughly in that front-loaded order. It is one dense paragraph rather than a structured list, which slightly hurts scanability for a tool with this much surface area.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 17 parameters and no output schema, the description must carry the return-shape burden, and it does: it enumerates the fields of both the brand row and the sighting row. Combined with the coverage of exclusions, auth, and billing, an agent has everything needed to call this correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all 17 parameters thoroughly, including defaults and limits. The description only restates the categories of optional input and adds no syntax or interaction detail beyond the schema, so baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource (find brands with recent public proof of paid placement in a niche) and names the exact evidence sources it reads. An agent knows precisely what the tool returns and on what basis, with no sibling tools to confuse it.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives concrete niche examples, notes what the optional inputs unlock (seed channels, feeds, event pages), and explicitly excludes Instagram, TikTok, and the Meta Ad Library. It also flags the APIFY_TOKEN prerequisite and the cost model. No alternatives exist to route against, so this is strong but stops short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v0.1.0- First observed
find_brand_sponsors
TDQS
Scored across 1 tool
There is only one tool, so there is no risk of selecting between overlapping operations. Its purpose is clearly stated as brand sponsor discovery.
The single tool uses a clear snake_case verb_noun pattern: find_brand_sponsors. There are no conflicting naming conventions within the set.
The single tool fits the narrow discovery purpose, but a one-tool surface is inherently thin and limits the server to one operation. It is not a trivial tool, but the set is at the low end for an MCP server.
For a read-only brand sponsor discovery server, the tool covers the core search use case with rich inputs and outputs. Minor gaps remain around follow-up operations such as retrieving or managing individual brand records, but they are not required for the stated purpose.
Maintenance
Related MCP Connectors
Public index of YouTube sponsorships: which brands sponsor which creators, from sampled videos.
YouTube sponsorship data: which brands sponsor which creators, and who to contact. Read only.
Find brands that sponsor podcasts and newsletters like yours, with dated public ad reads.
1Find brands that already sponsor newsletters like yours, with sponsorship rates.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceConnects a podcast-sponsorship database to AI assistants, allowing users to search for brands that sponsor podcasts and reveal buyer contacts by name and email.MIT
- AlicenseNot gradedqualityAmaintenanceEnables social media creators to pull TikTok, Instagram, Facebook, and YouTube analytics into a persistent vault, receive weekly digests, review scripts, build media kits, and draft brand outreach using official APIs only.MIT

Sponsorbook MCPofficial
AlicenseNot gradedqualityBmaintenanceEnables AI agents to research YouTube sponsors, inspect brands and their video evidence, explore overlapping creators and similar brands, manage research lists, and work with verified contacts.8 npmMIT- AlicenseAqualityCmaintenanceEnables agents to analyze X creators' niches, audiences and engagement, estimate sponsored-post prices with a transparent formula, rank creators against a brand brief, and run deals from offer through post verification to a recorded payout ledger. Every write is previewed and confirmed by a human, and the server never posts to X or moves money.161MIT