gconnect-mcp-all-v1
Enables connecting Claude.ai to Google Analytics and Google Ads through a unified MCP server, with per-operator Google account connections, read-only Ads REST v25 access, and a shared resolver for multiple Google product APIs.
README
gconnect-mcp-all-v1
True Model B Google Marketing MCP for Claude.ai Custom Connectors.
This is not a GA4-only connector and not a Google Ads-only connector. It is a shared platform with two product adapters now and a reserved extension point for DV360 later:
Operator
+-- Google Connection A
| +-- GA4 properties
| +-- Google Ads customers / MCC hierarchy
+-- Google Connection B
MCP JWT sub is always the internal operatorId. Google OpenID sub lives only on google_connections.googleSubjectId.
Architecture
flowchart TB
Claude["Claude.ai"]
McpAuth["MCP OAuth 2.1"]
Operator["operators operatorId"]
Resolver["ConnectionResolver"]
Ga4["GA4 adapter"]
Ads["Google Ads adapter"]
Dv360["DV360 future"]
Ga4Api["GA4 APIs"]
AdsApi["Ads REST v25"]
Claude --> McpAuth
McpAuth --> Operator
Operator --> Resolver
Resolver --> Ga4
Resolver --> Ads
Resolver -.-> Dv360
Ga4 --> Ga4Api
Ads --> AdsApi
See docs/architecture.md.
Identity
- MCP authentication answers: who is the operator?
- Google OAuth answers: which Google account is connected?
- Uniqueness is
(operatorId, googleSubjectId), never email and never a global Google subject.
Persistence
Firestore named database gconnect-mcp-all-v1 only.
Do not use (default) (V1) or ga4-mcp-v3 (V3). Startup rejects those IDs.
See docs/google-connections.md.
Local development
- Copy
.env.exampleto.envand fill placeholders. Do not copy secrets from V3. npm installnpm testnpm run typechecknpm run dev
Claude Custom Connector URL is http://localhost:3000/mcp. Health is GET /health.
Google Ads
Uses official Google Ads REST v25. Read-only. The app developer token is an application secret (GOOGLE_ADS_DEVELOPER_TOKEN), never a user OAuth credential.
The server resolves login-customer-id from discovered MCC hierarchy. Hyphenated customer IDs are normalized before API use.
See docs/google-ads.md and docs/ga4.md.
Deployment
Cloud Run, unauthenticated ingress, named Firestore database gconnect-mcp-all-v1.
.\scripts\cloud-run-setup.ps1 -ProjectId YOUR_PROJECT
.\scripts\cloud-run-deploy.ps1 -ProjectId YOUR_PROJECT
.\scripts\cloud-run-set-env.ps1 -ProjectId YOUR_PROJECT -AppBaseUrl https://... -GoogleClientId ... -GoogleClientSecret ... -McpTokenSecret ... -OauthStateSecret ... -TokenEncryptionKey ... -GoogleAdsDeveloperToken ...
See docs/deployment.md and docs/security.md.
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.
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.
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.
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.