A remote MCP server for searching YouTube sponsors and channels, letting an assistant find brands, creators, their collaborations and sponsorship activity.
What you can do
Search and inspect sponsors by name, tags, industry or activity, with detail, statistics and similar-brand lookups. Search and inspect YouTubers by subscribers, language, niches, sponsors and posting frequency, with detail and similar-creator lookups. See sponsorship relationships: which creators worked with a sponsor, which sponsors a creator has worked with, and recent sponsored videos or collaborations. Add channels individually or in bulk and poll import progress. Re-run sponsor detection on a channel or, on the agent plan, analyze its full video history.
When to use it
Useful for sponsorship research, influencer marketing planning, or checking which brands a channel promotes and which creators a brand has worked with. Worth adding when an assistant needs structured YouTube sponsorship data rather than general web search.
Requirements
A remote endpoint at api.meetsponsors.com over streamable HTTP; no packages, environment variables or headers are declared. A free tier exists, and some operations draw on a monthly MCP quota or a daily YouTube API budget.
Before you install
Some tools write data: adding channels triggers an enrichment pipeline, and refresh or full analysis consume quota (refresh costs 50 requests of the monthly MCP quota). Full analysis is limited to the agent plan. Bulk adds are capped at 50 channels per call and imports expire after 7 days. Prefer channel IDs to conserve the daily API budget.
Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/com.meetsponsors%2Fmcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.
Search sponsors by name, description, industry tags, or filters. Returns compact results (id, name, tagline = what the brand sells in a few words, website, niches, industryTags, country, operations, medianSubscribers). Use sponsor_get for full detail on a specific sponsor.
Get detailed information about a specific sponsor by ID. Strips raw scrape data and llm internal analysis blobs.
Parametersidrequired
sponsor_stats
Get statistics for a sponsor: number of YouTubers, median subscribers, operations per week/month/year
Parametersidrequired
sponsor_similar
Find sponsors similar to a given sponsor based on industry tags and niches. Returns compact format.
Parametersidrequiredlimit
sponsor_youtubers
Get YouTubers who have worked with a sponsor. Returns compact format.
Parametersidrequiredlimit
sponsor_mostActive
Get the most active sponsors in a given period (week/month/year), optionally filtered by language. Returns compact format.
Parameterslimitperiodlanguage
sponsor_recentVideos
Get the most recent sponsored videos from a sponsor, ordered by publication date
Parametersidrequiredlimit
sponsor_recentCollaborations
Get the most recent collaboration (one video per YouTuber) with a sponsor, sorted by publication date
Parametersidrequiredlimit
youtuber_search
Search YouTubers with advanced filters: subscribers, language, niches, sponsors worked with, monthly frequency, etc. All filters combine with AND — including hasWorkedWith, which keeps only creators who worked with EVERY listed domain. For "worked with brand A OR brand B", run one search per brand (or use sponsor_youtubers). Returns compact results. Use youtuber_get for full detail.
ParameterspagelimitnichessearchsortBycountrylanguagesortOrderhasWorkedWithmaxSubscribersminSubscribershasNotWorkedWith+3 more
youtuber_get
Get detailed information about a specific YouTuber by their YouTube channel ID. Includes llmDescription and llmSponsorProfile (LLM-friendly summaries), lastAnalyzedAt (when sponsors were last detected on the channel — every channel is re-scanned weekly; use youtuber_refresh if it is older than 7 days and you need fresher data), and lastFullAnalysisAt (last full-history analysis; null if never — see youtuber_fullAnalysis).
Parametersidrequired
youtuber_sponsors
Get sponsors a YouTuber has worked with, including video counts for each sponsor. Sorted by most recent sponsored video first (sortBy=lastVideo, default) or by first collaboration (sortBy=firstVideo). Paginated: use offset with limit (max 50 per page) and hasMore to walk big channels. Returns compact format.
Get the most recent sponsored videos from a YouTuber, with one video per sponsor (sorted by publication date)
Parametersidrequiredlimit
youtuber_similar
Find YouTubers similar to a given YouTuber based on content, niches, and sponsors. Returns compact format.
Parametersidrequiredlimit
youtuber_lastActiveBiggest
Get the biggest YouTubers who have been active recently (last 15 days) for a specific language. Returns compact format.
Parameterslimitlanguage
youtuber_add
Add a single YouTuber to the database and trigger the full enrichment pipeline (tags, niches, description, similarity, sponsor detection). Returns a batchId you can poll with import_status. Prefer passing a channel ID (UCxxxxxxxxxxxxxxxxxxxxxx, 24 chars) — handles ('@xxx') and URLs work too but cost an extra YouTube API quota point per call to resolve.
Parametersinputrequired
youtuber_bulk_add
Add up to 50 YouTubers in one call and trigger enrichment for each. Returns a batchId you can poll with import_status. Strongly prefer channel IDs (UCxxxxxxxxxxxxxxxxxxxxxx, 24 chars) over handles/URLs — handles cost an extra YouTube API quota point each, which depletes the daily 10k budget faster.
Parametersinputsrequired
youtuber_refresh
Re-run sponsor detection on a YouTuber already in the database (latest videos). Costs 50 requests of your monthly MCP quota. Refused when the channel was analyzed less than 7 days ago — every channel is re-scanned weekly, so check lastAnalyzedAt from youtuber_get first. Runs in the background (a few minutes); call youtuber_get / youtuber_sponsors afterwards. For a channel not in the database yet, use youtuber_add.
Parametersidrequired
youtuber_fullAnalysis
Agent plan only. Run sponsor detection on the ENTIRE video history of a YouTuber already in the database (not just the latest videos like youtuber_refresh), and re-check older automatic rejections with the current detection pipeline — use it when youtuber_sponsors looks incomplete for a channel with a long sponsorship history. Costs 200 requests of your monthly MCP quota. Refused when the channel had a full analysis less than 30 days ago (check lastFullAnalysisAt from youtuber_get first). Runs in the background (from several minutes to an hour on big channels); when lastFullAnalysisAt in youtuber_get moves, youtuber_sponsors reflects the result. For a channel not in the database yet, use youtuber_add.
Parametersidrequired
import_status
Poll the progress of a bulk import batch by its batchId. Returns total/queued/done/failed counts plus startedAt/finishedAt timestamps. Batches expire after 7 days.
ParametersbatchIdrequired
Version history
1
v1.0.0LatestSep 16, 2026
Score
83%
83% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
Reached in the last 30 daysRequired25 pts
Auth declaredRequired10 pts
Tools listedRequired15 pts
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
LicenseNot applicable
A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.