George Weale
d9e930e823
* docs(integrations): fix unresolvable imports and stale API claims * docs: apply style pass and drop out-of-scope import cleanup * docs(integrations): address review feedback on gcs, cloud-trace, reflect-and-retry Restore the gcs_ tool name prefixes in the GCS tool tables, since both toolsets set tool_name_prefix="gcs" and the tables list names as the model sees them. Use the current Agent Platform SDK name in cloud-trace prose, make the reflect-and-retry failure description language-neutral for Python and Go, and drop the redundant re-export clause. * docs(gcs): note that tool_filter matches unprefixed tool names Tool filtering runs inside get_tools() against the unprefixed name, and get_tools_with_prefix() applies the gcs_ prefix afterwards, so the names in the tables are not the names tool_filter expects. * docs(computer-use): drop unused Gemini and override imports --------- Co-authored-by: Kristopher Overholt <koverholt@google.com>
4.7 KiB
catalog_title, catalog_description, catalog_icon, catalog_tags
| catalog_title | catalog_description | catalog_icon | catalog_tags | ||
|---|---|---|---|---|---|
| Windsor.ai | Query and analyze marketing, sales, and customer data from 325+ platforms | /integrations/assets/windsor-ai.png |
|
Windsor.ai MCP tool for ADK
The Windsor MCP Server connects your ADK agent to Windsor.ai, a data integration platform that unifies marketing, sales, and customer data from 325+ sources. This integration gives your agent the ability to query and analyze cross-channel business data using natural language, without writing SQL or custom scripts.
Use cases
-
Marketing Performance Analysis: Analyze campaign performance across channels like Facebook Ads, Google Ads, TikTok Ads, and more. Ask questions like "What campaigns had the best ROAS last month?" and get instant insights.
-
Cross-Channel Reporting: Generate comprehensive reports combining data from multiple platforms such as GA4, Shopify, Salesforce, and HubSpot to get a unified view of business performance.
-
Budget Optimization: Identify underperforming campaigns, detect budget inefficiencies, and get AI-driven recommendations for spend allocation across advertising channels.
Prerequisites
- A Windsor.ai account with connected data sources
- A Windsor.ai API key (obtain from onboard.windsor.ai)
Use with agent
=== "Python"
=== "Remote MCP Server"
```python
from google.adk.agents import Agent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import StreamableHTTPConnectionParams
WINDSOR_API_KEY = "YOUR_WINDSOR_API_KEY"
root_agent = Agent(
model="gemini-flash-latest",
name="windsor_agent",
instruction="Help users analyze their marketing and business data.",
tools=[
McpToolset(
connection_params=StreamableHTTPConnectionParams(
url="https://mcp.windsor.ai",
headers={
"Authorization": f"Bearer {WINDSOR_API_KEY}",
},
),
)
],
)
```
=== "TypeScript"
=== "Remote MCP Server"
```typescript
import { LlmAgent, MCPToolset } from "@google/adk";
const WINDSOR_API_KEY = "YOUR_WINDSOR_API_KEY";
const rootAgent = new LlmAgent({
model: "gemini-flash-latest",
name: "windsor_agent",
instruction: "Help users analyze their marketing and business data.",
tools: [
new MCPToolset({
type: "StreamableHTTPConnectionParams",
url: "https://mcp.windsor.ai",
transportOptions: {
requestInit: {
headers: {
Authorization: `Bearer ${WINDSOR_API_KEY}`,
},
},
},
}),
],
});
export { rootAgent };
```
Capabilities
Windsor MCP provides a natural language interface to your integrated business data. Rather than exposing discrete tools, it interprets your questions and returns structured insights from your connected data sources.
| Capability | Description |
|---|---|
| Data querying | Query normalized data from any of your 325+ connected platforms |
| Performance analysis | Analyze KPIs, trends, and campaign metrics across channels |
| Report generation | Create marketing dashboards and cross-channel performance reports |
| Budget analysis | Identify spend inefficiencies and get optimization recommendations |
| Anomaly detection | Detect outliers and unusual patterns in performance data |
Supported data sources
Windsor.ai connects to 325+ platforms, including:
- Advertising: Facebook Ads, Google Ads, TikTok Ads, LinkedIn Ads, Microsoft Ads
- Analytics: Google Analytics 4, Adobe Analytics
- CRM: Salesforce, HubSpot
- E-commerce: Shopify
- And more: See the full list of connectors on the Windsor.ai website