google_ads_mcp vs everything
Side-by-side comparison to help you pick between these two MCP servers.
google_ads_mcp by google-marketing-solutions | everything by modelcontextprotocol | |
|---|---|---|
| Stars | ★ 203 | ★ 85,748 |
| 30d uses | — | — |
| Score | 46 | 77 |
| Official | — | ✓ |
| Categories | E-commerceAI / LLM ToolsDeveloper Tools | Developer ToolsAI / LLM ToolsOther |
| Language | Python | TypeScript |
| Last commit | this month | this month |
google_ads_mcp · Summary
Google Ads MCP server enables LLMs to interact with Google Ads API via GAQL queries and ad management tools.
everything · Summary
Official MCP test server exercising all protocol features for client builders.
google_ads_mcp · Use cases
- Automate Google Ads reporting by querying campaign metrics through natural language
- Create and manage advertising campaigns directly through conversational AI interfaces
- Generate performance insights across multiple Google Ads accounts
everything · Use cases
- Testing MCP client implementations against all protocol features
- Learning MCP protocol capabilities through a reference server
- Validating client compatibility with different transport methods
google_ads_mcp · Install
Installation
- Install Python 3.12 with pipx or uv
- Set up Google Ads credentials in a
google-ads.yamlfile with required credentials - Configure environment variables (optional):
ADS_MCP_ENABLE_MUTATIONS,GOOGLE_ADS_CREDENTIALS,USE_GOOGLE_OAUTH_ACCESS_TOKEN
Launch with pipx
pipx run --spec git+https://github.com/google-marketing-solutions/google_ads_mcp.git run-mcp-serverLocal development
uv pip sync
uv run -m ads_mcp.serverClaude Desktop Configuration
{
"mcpServers": {
"GoogleAds": {
"command": "pipx",
"args": [
"run",
"--spec",
"git+https://github.com/google-marketing-solutions/google_ads_mcp.git",
"run-mcp-server"
],
"env": {
"GOOGLE_ADS_CREDENTIALS": "PATH_TO_YAML"
},
"timeout": 30000
}
}
}everything · Install
NPX (recommended)
{
"mcpServers": {
"everything": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-everything"]
}
}
}On Windows, use cmd /c:
{
"mcpServers": {
"everything": {
"command": "cmd",
"args": ["/c", "npx", "-y", "@modelcontextprotocol/server-everything"]
}
}
}Docker
{
"mcpServers": {
"everything": {
"command": "docker",
"args": ["run", "-i", "--rm", "mcp/everything"]
}
}
}Global install
npm install -g @modelcontextprotocol/server-everything@latest
npx @modelcontextprotocol/server-everything