Google Ads MCP Server Open-Sources Ad Operations for AI Agents
The googleads/google-ads-mcp repository provides source code for an MCP server that connects LLMs and AI agents to the Google Ads API. Its tools support GAQL searches, resource metadata, customer access, asset creation, video uploads, and label management, with write operations guarded by a two-step propose-and-confirm workflow. The repository documentation also describes local stdio and remote HTTP deployment options.
According to the repository, this is a deployable integration that lets AI agents query advertising accounts and perform selected Google Ads operations while requiring explicit confirmation for mutations.
Google Ads MCP Server
This repo contains the source code for running an MCP server that interacts with the Google Ads API.
Tools
The server uses the Google Ads API to provide several Tools and Resources for use with LLMs and AI agents.
Tools available
search: Retrieves information about the Google Ads account using GAQL.get_resource_metadata: Retrieves metadata about a Google Ads API resource type, for example "campaign". This is useful to understand the structure of the data and what fields are available for querying.list_accessible_customers: Returns IDs of customers directly accessible by the user authenticating the call.create_asset: Creates Google Ads assets (TEXT,IMAGE,YOUTUBE_VIDEO,SITELINK,CALLOUT,STRUCTURED_SNIPPET, and other asset types viaextra_params). Note:image_asset_pathis supported in localstdiomode only; use base64image_asset_datafor remote HTTP deployments.upload_video_asset: Uploads a local video file to YouTube via the Google Ads API using a background task so it can be referenced by video assets (supported in localstdiomode only).manage_labels: Creates, updates, and removes account labels.manage_label_associations: Creates and removes label associations onCAMPAIGN,CUSTOMER,AD_GROUP, andAD_GROUP_CRITERIONresources.
#Google Ads MCP Server#Google Ads API#FastMCP#Codex CLI#Antigravity