Name: Brand Sponsor Finder
Author: Mamba Labs

Brand Sponsor Finder MCP Hosted by mcprush

Brands paying creators in a niche, with evidence links, dates, and recency scores.

Grade A Remote · Streamable HTTP Buyer key + your own key 1 tool v0.1.0 · 29 Oct 2026 MIT

No reviews yet by Mamba Labsnpm Hosted here, behind our gateway

Tools

find_brand_sponsors

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 br

niche 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

audience_keywords 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.

window_days string

Only sightings from the last N days. Whole number, default 90, at most 365. Sent as text so Clay works. Default 90.

sources 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 fou

seed_sources 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.

event_calendar 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": "..."}],

use_niche_presets 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.

include_brands 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.

include_sightings string

true or false, default true. One row per sighting with its evidence link, date, promo code, placement type, and pitch angle. Default true.

max_channels string

YouTube channels read per run. Whole number, default 20, at most 100. Sent as text so Clay works. Default 20.

max_videos_per_channel 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.

max_podcasts string

Podcast shows read per run. Whole number, default 15, at most 100. Sent as text so Clay works. Default 15.

max_episodes_per_podcast string

Newest episodes read per show. Whole number, default 8, at most 30. Sent as text so Clay works. Default 8.

max_newsletters string

Newsletters read per run. Whole number, default 8, at most 50. Sent as text so Clay works. Default 8.

max_issues_per_newsletter string

Newest issues read per newsletter. Whole number, default 8, at most 30. Sent as text so Clay works. Default 8.

max_brands_to_check 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.

max_charge_usd string

Optional. The run stops before it would charge more than this.

max_rows string

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.

cursor string

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 a

Arguments

A call is made on an account: it counts against an allowance and the publisher sees it, which is why this one asks who you are first.

96/100

trust score

tool declared

remote

via our gateway

—

p95 latency

What it does

Find the brands already paying creators in a niche, pulled from YouTube descriptions, podcast show notes, newsletters, event sponsor pages, and creator programs. Each row carries evidence links, dates, and a recency score.

Quickstart

# 1 — sign in once: npx mcprush@latest login
#     it asks for a key from mcprush.com/dashboard#access
# 2 — install
npx mcprush@latest add mambalabs/brand-sponsor-finder-mcp

# 3 — ask your agent for something these tools do
#   find_brand_sponsors

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither.

Brand Sponsor Finder costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publisher

Mamba Labs103 servers

11 categories · publishing since 2026

All 103 servers

Installation

Where are you running it?

Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine — this server runs on infrastructure we host behind our gateway, and what you install is the connection to it.

Claude Codenot declared — it may still work

Claude Code has its own MCP command, and the key rides on it as a header — the gateway refuses a call that carries none. Claude Code reads MCPRUSH_KEY each time it connects, so the key stays out of its config: export your key from Access in your shell profile (macOS, Linux), or run setx MCPRUSH_KEY <your key> and open a new terminal (Windows). Or let npx mcprush@latest add mambalabs/brand-sponsor-finder-mcp write the entry with the key for you; --scope user makes it available in every project. The first connection after a quiet spell starts the server, which takes up to a minute: if your client says it failed to connect, reconnect after that (/mcp in Claude Code).

claude mcp add --transport http --scope user mcp-brand-sponsor-finder https://mcprush.com/gw/mcp-brand-sponsor-finder/mcp --header 'Authorization: Bearer ${MCPRUSH_KEY}'

Reconnect, or start a new session, and the tools appear in the model’s tool list.

Free to install on mcprush: no card. The gateway still answers a key, so you sign in once — which is also what gives you saved lists, release alerts and a budget cap.

What it asks of you

It reaches a system of yours, so it needs your own credential rather than the publisher’s: APIFY_TOKEN — Your Apify API token. Runs are billed to your own Apify account.. You set it after installing; the value is sealed here and handed to the server when it starts.

What it writes

One config entry pointing at the gateway. The server itself runs on infrastructure we host, so nothing from this listing executes on your machine.

What you approve

1 tool, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

Parameter	Type	Required	Notes
niche	string	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
audience_keywords	string	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.
window_days	string	no	Only sightings from the last N days. Whole number, default 90, at most 365. Sent as text so Clay works. Default 90.
sources	string	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 fou
seed_sources	string	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	string	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": "..."}],
use_niche_presets	string	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.
include_brands	string	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.
include_sightings	string	no	true or false, default true. One row per sighting with its evidence link, date, promo code, placement type, and pitch angle. Default true.
max_channels	string	no	YouTube channels read per run. Whole number, default 20, at most 100. Sent as text so Clay works. Default 20.
max_videos_per_channel	string	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_podcasts	string	no	Podcast shows read per run. Whole number, default 15, at most 100. Sent as text so Clay works. Default 15.
max_episodes_per_podcast	string	no	Newest episodes read per show. Whole number, default 8, at most 30. Sent as text so Clay works. Default 8.
max_newsletters	string	no	Newsletters read per run. Whole number, default 8, at most 50. Sent as text so Clay works. Default 8.
max_issues_per_newsletter	string	no	Newest issues read per newsletter. Whole number, default 8, at most 30. Sent as text so Clay works. Default 8.
max_brands_to_check	string	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_charge_usd	string	no	Optional. The run stops before it would charge more than this.
max_rows	string	no	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.
cursor	string	no	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 a

Free

$0 forever

Every tool, no call limit, and mcprush charges nothing
A buyer key from your dashboard — the gateway refuses a call without one
Answers through our gateway, so every call is in your log
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install Brand Sponsor Finder or to call it, and its free tier carries no monthly call limit.

ATrust score 96 / 100

Scanned: 1.1.0 · 29 Oct 2026

Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.

Threat score100

Client score96

Findings1 threat · 0 capability

Capabilitymoderate

Coveragesource

Verificationrepo

Surface digesta93f46b7fc33b75ab1e5d4df60e44b3fc3b4176f9cee39c45d17fbb90ab5fa93

Score vectorthreat 100 → client 96

Term	Level	What it prices	Points
capability-exposure	moderate	capability blast radius (moderate) — client exposure if the model is manipulated	−3
verification-discount	repo	publisher verification (public source) — no provenance, but the source is public and inspectable	−1
coverage-honesty	source	inspection depth (source) — how much of the target the scan could see	−0

score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.

What the scan could actually read

A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.

Tool surfaceread

Implementation sourceread

Package metadataread

Live transportnot available

Tools were statically extracted from the published source (1 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".

Capability — what it could do if the model were manipulated

Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.

Tool	Capability tags	Why the tag was assigned
find_brand_sponsors	untrusted-input	untrusted-input: declares openWorldHint: true (interacts with entities outside the server)

Toxic-flow graph

The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.

The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.

Supply chain and provenance

Integrityfirst-seen

Surface digesta93f46b7fc33b75a

Scanned2026-10-29

This is the first scan of this surface here, so there is nothing yet to compare it against.

Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.