Skip to main content
Glama
Brand Sponsor Finder MCP Server

Brand Sponsor Finder MCP Server

Find brands paying creators in a niche, with evidence

find_brand_sponsors
Read-only

Finds brands with recent paid placements in a niche from YouTube descriptions, podcast notes, newsletters, event pages, job posts, creator programs, returns evidence-linked brand and sighting rows.

Instructions

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. ROW CAP AND PAGING: a call returns at most max_rows rows (default 50, at most 200) as a JSON array in the first content block, and a paging block in the second with total_rows and next_cursor. To get every row, call again with only cursor set to next_cursor until next_cursor is null. A cursor call reads the same finished run's rows, starts no new run, and is not billed again. 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.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "find_brand_sponsors"
  }
}

Input Schema

NameRequiredDescriptionDefault
nicheNoThe 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).
cursorNoWrapper setting, not sent to the actor. The next_cursor from the previous call's paging block. With a cursor the call starts no run and returns the next page of that run's rows, so nothing is billed again; every other input except max_rows is ignored.
sourcesNoOptional. 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.
max_rowsNoWrapper setting, not sent to the actor. Rows returned per call: whole number, default 50, at most 200. Reach the rest of the run's rows with cursor.
window_daysNoOnly sightings from the last N days. Whole number, default 90, at most 365. Sent as text so Clay works. Default 90.
max_channelsNoYouTube channels read per run. Whole number, default 20, at most 100. Sent as text so Clay works. Default 20.
max_podcastsNoPodcast shows read per run. Whole number, default 15, at most 100. Sent as text so Clay works. Default 15.
seed_sourcesNoOptional. 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_calendarNoOptional. 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_brandsNotrue 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_usdNoOptional. The run stops before it would charge more than this.
max_newslettersNoNewsletters read per run. Whole number, default 8, at most 50. Sent as text so Clay works. Default 8.
audience_keywordsNoOptional. 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_sightingsNotrue or false, default true. One row per sighting with its evidence link, date, promo code, placement type, and pitch angle. Default true.
use_niche_presetsNotrue 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_checkNoBrands, 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_channelNoNewest 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_podcastNoNewest episodes read per show. Whole number, default 8, at most 30. Sent as text so Clay works. Default 8.
max_issues_per_newsletterNoNewest issues read per newsletter. Whole number, default 8, at most 30. Sent as text so Clay works. Default 8.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.1.0
    • addedInput schema / properties / cursor
      Added value: +{
      +  "description": "Wrapper setting, not sent to the actor. The next_cursor from the previous call's paging block. With a cursor the call starts no run and returns the next page of that run's rows, so nothing is billed again; every other input except max_rows is ignored.",
      +  "type": "string"
      +}
    • addedInput schema / properties / max_rows
      Added value: +{
      +  "description": "Wrapper setting, not sent to the actor. Rows returned per call: whole number, default 50, at most 200. Reach the rest of the run's rows with cursor.",
      +  "type": "string"
      +}
  2. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well past the annotations: discloses the billing model (per brand row, per sighting row, per run start), that cursor calls start no run and are not billed again, the APIFY_TOKEN requirement, the max_charge_usd circuit breaker, and the error contract (free input_invalid row, failed run returned as an error with run ID). Nothing contradicts readOnlyHint=true or idempotentHint=false; describing a new run per fresh call is consistent with non-idempotency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the purpose, then source coverage, then the return shape, then paging, then cost/auth/error behavior in a deliberate order. Sentences are dense but each carries an operational fact; the only mild redundancy is restating row contents that the parameters also describe.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 19 parameters and no output schema, the description carries the return-shape burden and does so: one row per brand domain with named fields, one row per sighting with named fields, plus a paging block with total_rows and next_cursor. Cost, auth, failure modes, and source exclusions are all covered, so an agent can call it correctly on the first attempt.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description still adds framing the schema does not, namely why values are sent as text (Clay interoperability), the cursor rule that all other inputs except max_rows are ignored, and that max_charge_usd aborts the run rather than truncating output. Some prose (two row types, defaults) duplicates the schema, keeping it out of 5 territory.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

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 immediately names the evidence set and both return row types. No siblings exist, but the scope is unambiguous: it is a sponsor-discovery search over named sources, not a lookup or a general web search.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explains required input (a niche), optional wideners (audience_keywords, seed_sources, event_calendar), and the run-vs-cursor alternation for paging. It also draws explicit boundaries by excluding Instagram, TikTok, and the Meta Ad Library, which prevents mis-selection. It lacks an explicit 'do not use when' statement, so it 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.

Deploy Server

Other Tools