Connect
Optimize
Secure
Google Analytics MCP Server
for AI Agents
Production-ready Google Analytics MCP server with 32 extensible actions — plus built-in authentication, security, and optimized execution.
Google Analytics MCP Server
Built by 
StackOne
StackOne 
Coverage
32 Agent Actions
Create, read, update, and delete across Google Analytics — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Google Analytics MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Google Analytics tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Google Analytics call.
Tools Discovery →What is the Google Analytics MCP Server?
A Google Analytics MCP server lets AI agents read and write Google Analytics data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Google Analytics MCP server ships with 32 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All Google Analytics MCP Tools and Actions
Every action from Google Analytics's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Accounts
- List Accounts
List all Google Analytics accounts accessible to the authenticated user
- Get Account
Get details of a specific Google Analytics account by its resource name
Propertys
- Create Property
Create a new Google Analytics 4 property under an account
- Get Property
Get details of a specific Google Analytics 4 property by its resource name
- Update Property
Update settings of an existing Google Analytics 4 property
Run Reports
- Batch Run Reports
Run multiple Google Analytics reports in a single API call
- Run Report
Run a customized report on Google Analytics 4 data for a property
Data Streams
- Create Data Stream
Create a new data stream for a Google Analytics 4 property
- List Data Streams
List all data streams for a Google Analytics 4 property
- Get Data Stream
Get details of a specific data stream by its full resource name
- Delete Data Stream
Delete a data stream from a Google Analytics 4 property
Measurement Protocol Secrets
- Create Measurement Protocol Secret
Create a Measurement Protocol secret for a Google Analytics 4 data stream
- List Measurement Protocol Secrets
List all Measurement Protocol secrets for a Google Analytics 4 data stream
- Get Measurement Protocol Secret
Get details of a specific Measurement Protocol secret by its full resource name
- Delete Measurement Protocol Secret
Delete a Measurement Protocol secret from a Google Analytics 4 data stream
Audience Exports
- Create Audience Export
Create an audience export for a Google Analytics 4 property
- List Audience Exports
List all audience exports for a Google Analytics 4 property
- Get Audience Export
Get details of a specific audience export by its full resource name
- Query Audience Export
Query user data from an ACTIVE audience export
Key Events
- Create Key Event
Create a new key event for a Google Analytics 4 property
- List Key Events
List all key events for a Google Analytics 4 property
- Get Key Event
Get details of a specific key event by its full resource name
- Delete Key Event
Delete a key event from a Google Analytics 4 property
Other (9)
- List Account Summaries
List summaries of all accounts and their properties accessible to the authenticated user
- Get Data Sharing Settings
Get data sharing settings for a Google Analytics account
- List Properties
List all Google Analytics 4 properties under an account
- Get Data Retention Settings
Get data retention settings for a Google Analytics 4 property
- Get Metadata
Get metadata about dimensions and metrics available for a GA4 property
- Acknowledge User Data Collection
Acknowledge user data collection terms for a Google Analytics 4 property
- Run Realtime Report
Run a realtime report on active users currently on a GA4 property
- Run Pivot Report
Run a pivot report to summarize Google Analytics data with cross-tabulated dimensions
- Patch Key Event
Update a key event's counting method or default value
Set Up Your Google Analytics MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Google Analytics in under 10 lines of code.
MCP Clients
Agent Frameworks
JSON{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}More Data & Analytics MCP Servers
Tableau
114+ actions
SurveyMonkey
104+ actions
Microsoft Excel
101+ actions
Qlik
100+ actions
Snowflake
80+ actions
PostHog
63+ actions
Amplitude
53+ actions
Google Analytics MCP Server Resources
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
Google Analytics MCP Server FAQ
Google Analytics MCP server vs direct API integration — what's the difference?
A Google Analytics MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Google Analytics. A Google Analytics MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Google Analytics at runtime. StackOne provides both.
How does Google Analytics authentication work for AI agents?
Google Analytics authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Google Analytics account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Google Analytics MCP tools vulnerable to prompt injection?
Yes — Google Analytics MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Google Analytics agent and how do I avoid it?
Context bloat happens when Google Analytics tool schemas and API responses eat your Google Analytics agent's memory, preventing it from reasoning effectively. A single Google Analytics query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Google Analytics agent can access?
Yes — you can limit which actions your Google Analytics agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Google Analytics MCP server?
Yes — you can create custom agent actions for your Google Analytics MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Google Analytics's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Google Analytics MCP server?
Skip a Google Analytics MCP server if your integration is purely software-to-software — direct Google Analytics API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Google Analytics actions at runtime.
What AI frameworks and AI clients does the StackOne Google Analytics MCP server support?
The StackOne Google Analytics MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.