Andrew Yim
236be6c580
🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
95 lines
3.6 KiB
Markdown
95 lines
3.6 KiB
Markdown
# MCP Servers Overview for GA Agent
|
|
|
|
## Available MCP Servers
|
|
|
|
### Google Analytics MCP Servers
|
|
|
|
| Server | Language | Source | Status |
|
|
|--------|----------|--------|--------|
|
|
| **google-analytics-mcp** (Official) | Python | [googleanalytics/google-analytics-mcp](https://github.com/googleanalytics/google-analytics-mcp) | Recommended |
|
|
| mcp-server-google-analytics | TypeScript | [ruchernchong/mcp-server-google-analytics](https://github.com/ruchernchong/mcp-server-google-analytics) | Community |
|
|
|
|
**Official Google GA MCP Features:**
|
|
- Real-time reporting
|
|
- Custom/standard dimensions/metrics
|
|
- Natural language queries (e.g., "top products by revenue")
|
|
- `order_by` support
|
|
- OAuth + Service Account auth
|
|
|
|
### BigQuery MCP Servers
|
|
|
|
| Server | Language | npm | Status |
|
|
|--------|----------|-----|--------|
|
|
| **@ergut/mcp-bigquery-server** | Node.js | `npx -y @ergut/mcp-bigquery-server` | Recommended |
|
|
| mcp-server-bigquery | Python | - | Alternative |
|
|
| Google MCP Toolbox | Python | - | Official (multi-DB) |
|
|
|
|
**ergut/mcp-bigquery-server Features:**
|
|
- Read-only secure access
|
|
- Schema discovery
|
|
- Natural language to SQL
|
|
- 1GB query limit
|
|
|
|
## Recommended Stack
|
|
|
|
For our GA Agent, we recommend:
|
|
|
|
```
|
|
┌─────────────────────────────────────────────────────┐
|
|
│ Claude Code │
|
|
│ │ │
|
|
│ ┌───────────┴───────────┐ │
|
|
│ ▼ ▼ │
|
|
│ ┌─────────────────┐ ┌─────────────────┐ │
|
|
│ │ Google Analytics│ │ BigQuery │ │
|
|
│ │ MCP Server │ │ MCP Server │ │
|
|
│ └────────┬────────┘ └────────┬────────┘ │
|
|
│ │ │ │
|
|
│ ▼ ▼ │
|
|
│ ┌─────────────────┐ ┌─────────────────┐ │
|
|
│ │ GA4 Data API │ │ BigQuery API │ │
|
|
│ │ GA4 Admin API │ │ (GA4 Export) │ │
|
|
│ └─────────────────┘ └─────────────────┘ │
|
|
└─────────────────────────────────────────────────────┘
|
|
```
|
|
|
|
## Why Both?
|
|
|
|
1. **GA4 MCP** - Direct API access for:
|
|
- Real-time data
|
|
- Quick metrics queries
|
|
- Account/property management
|
|
|
|
2. **BigQuery MCP** - For advanced analysis:
|
|
- Historical data (GA4 → BigQuery export)
|
|
- Complex SQL queries
|
|
- Cross-dataset joins
|
|
- Large-scale analysis
|
|
|
|
## Prerequisites
|
|
|
|
### Google Cloud Setup
|
|
|
|
1. Create a Google Cloud Project (or use existing)
|
|
2. Enable these APIs:
|
|
- Google Analytics Data API
|
|
- Google Analytics Admin API
|
|
- BigQuery API
|
|
|
|
3. Create Service Account:
|
|
- Go to IAM & Admin → Service Accounts
|
|
- Create new service account
|
|
- Grant roles:
|
|
- `Analytics Viewer` (or Admin for write ops)
|
|
- `BigQuery Data Viewer`
|
|
- `BigQuery Job User`
|
|
- Download JSON key file
|
|
|
|
4. Grant GA4 Access:
|
|
- In GA4 Admin → Property Access Management
|
|
- Add service account email with Viewer role
|
|
|
|
## Next Steps
|
|
|
|
See `02-setup-guide.md` for installation instructions.
|