Vibe.co MCP Server

Vibe.co MCP Server

Enables AI assistants to interact with the Vibe CTV/streaming advertising platform, allowing listing of advertisers, apps, campaigns, and creating reports via the Vibe API.

Category
Visit Server

README

Vibe.co MCP Server

CI Coverage Status CodeQL OpenSSF Scorecard npm version npm downloads License Node

A Model Context Protocol (MCP) server for the Vibe CTV/streaming advertising platform.

This server allows AI assistants (like Claude) to interact with your Vibe advertising data securely via the Vibe Streaming API.

Quick Start

Prerequisites

  • Node.js v22 or higher
  • A Vibe account with API access
  • A Vibe API key (see Step 1)

Step 1: Get a Vibe API Key

  1. Log in to your Vibe account
  2. Navigate to Developer Tool > API Keys
  3. Create or copy your API key

Step 2: Configure Your MCP Client

Choose the setup that matches your MCP client:

Claude Desktop (Recommended)

Add to your claude_desktop_config.json:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "vibe": {
      "command": "npx",
      "args": ["-y", "vibeco-mcp"],
      "env": {
        "VIBE_API_KEY": "your-api-key"
      }
    }
  }
}

Claude Code (CLI)

Add to your Claude Code MCP settings (~/.claude/mcp.json or project-level):

{
  "mcpServers": {
    "vibe": {
      "command": "npx",
      "args": ["-y", "vibeco-mcp"],
      "env": {
        "VIBE_API_KEY": "your-api-key"
      }
    }
  }
}

Cursor

In Cursor settings, add an MCP server:

{
  "mcpServers": {
    "vibe": {
      "command": "npx",
      "args": ["-y", "vibeco-mcp"],
      "env": {
        "VIBE_API_KEY": "your-api-key"
      }
    }
  }
}

Configuration Reference

Environment Variables

Variable Required Default Description
VIBE_API_KEY Yes - Vibe API key
VIBE_API_BASE_URL No https://clear-platform.vibe.co/rest/reporting/v1 API base URL (override for testing)
MCP_TRANSPORT No stdio Transport mode: stdio or http
MCP_SERVER_HOST No 127.0.0.1 Host to bind the HTTP server to
MCP_SERVER_PORT No 3000 Port for the HTTP server

Features

Tools

The server provides 8 tools for full Vibe API coverage:

Connectivity

Tool Description
vibe.ping Check server status and API key configuration

Advertisers

Tool Description
vibe.advertisers.list List all advertiser IDs

Apps

Tool Description
vibe.apps.list List app IDs for an advertiser

Campaigns

Tool Description
vibe.campaigns.list List campaign details for an advertiser

Reports

Tool Description
vibe.reports.create Create an async report (rate limited: 15/hr)
vibe.reports.status Check report status and get download URL

Purchases

Tool Description
vibe.purchases.list List purchase IDs for an advertiser

Resources

The server exposes data as MCP resources:

Static Resources

Resource URI Description
vibe://advertisers List all advertiser IDs

Resource Templates

Resource URI Description
vibe://advertisers/{advertiser_id}/apps App IDs for a specific advertiser
vibe://advertisers/{advertiser_id}/campaigns Campaign details for a specific advertiser

Prompts

The server provides guided prompts for common workflows:

Prompt Description
campaign-report Guided workflow for creating a campaign performance report
setup-api-key Instructions for configuring the Vibe API key

Development

Setup

# Clone the repo
git clone https://github.com/jacob-hartmann/vibeco-mcp.git
cd vibeco-mcp

# Use the Node.js version from .nvmrc
# (macOS/Linux nvm): nvm install && nvm use
# (Windows nvm-windows): nvm install 22 && nvm use 22
nvm install
nvm use

# Install dependencies
pnpm install

# Copy .env.example and configure
cp .env.example .env
# Edit .env with your API key

Running Locally

# Development mode (auto-reload)
pnpm dev

# Production build
pnpm build

# Production run
pnpm start

Debugging

You can use the MCP Inspector to debug the server:

# Run from source
pnpm inspect

# Run from built output
pnpm inspect:dist

pnpm inspect loads .env automatically via dotenv (see .env.example).

Contributing

Contributions are welcome! Please see CONTRIBUTING.md for guidelines on how to contribute to this project.

Security

See SECURITY.md for security policy and reporting vulnerabilities.

Support

This is a community project provided "as is" with no guaranteed support. See SUPPORT.md for details.

License

MIT © Jacob Hartmann

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured