Sponsorbook MCP
Enables 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.
README
Sponsorbook MCP
Research YouTube sponsors from Claude, Codex, Cursor, and other MCP clients.
Sponsorbook MCP lets your agent find sponsors, inspect the videos and creators behind each relationship, explore similar brands, manage research lists, and work with verified contacts.
What you can do
- Find sponsor brands by name, domain, language, recency, volume, and typical views.
- Inspect a brand's sponsorship history and the supporting video evidence.
- Explore creators a brand sponsors and brands with overlapping creator relationships.
- Search YouTube channels and see which brands have sponsored them.
- Create lists, save brands, and attach research notes.
- View masked contacts, explicitly reveal a stored email, or request a contact when none exists.
Connect
Sponsorbook MCP requires a Sponsorbook Pro workspace.
Remote MCP
Use the hosted endpoint when your client supports remote MCP with authentication:
https://app.sponsorbook.io/mcp
Local MCP configuration
For clients that launch a local MCP command:
{
"mcpServers": {
"sponsorbook": {
"command": "npx",
"args": ["-y", "@sponsorbook/mcp"]
}
}
}
Your browser opens on the first connection so you can sign in and choose your Sponsorbook workspace. Later connections reuse that authorization.
Requirements
- Node.js 20.18.1 or newer for the local package
- A Sponsorbook Pro workspace
How it works
The package is a small open-source bridge for MCP clients that launch local commands. Sponsorbook's hosted MCP server performs the research and applies the same workspace permissions, contact reveal rules, and catalogue limits as the web app.
The hosted server and Sponsorbook catalogue are separate from this repository.
Development
npm install
npm test
npm run test:live
Set SPONSORBOOK_MCP_URL to an HTTPS endpoint, or to an HTTP localhost endpoint, when testing another Sponsorbook deployment.
Security
Please report vulnerabilities through GitHub private vulnerability reporting.
Licence
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.