Pipeboard is a connector that fronts the major ad platforms over MCP. Its Google Ads endpoint reads campaign performance, keywords, and ad groups through one Pipeboard sign-in. clariBI already has a native Google Ads data source over OAuth; the Pipeboard connector is an alternative MCP path for teams that prefer to route their ad data through Pipeboard.
Why connect Pipeboard
Some teams already authorize their ad accounts once at Pipeboard and want the same token to feed analytics rather than setting up a second direct connection.
With Pipeboard connected, you can ask "Which Google Ads campaigns spent the most last week?", "What is cost per conversion by ad group?", or "Which keywords burned budget without converting?" and the AI engine reads the campaign data live.
How the connection works
clariBI talks to Pipeboard through its hosted MCP server at https://google-ads.mcp.pipeboard.co/. Authentication uses an OAuth flow that clariBI registers itself for (no developer console setup on your side). Tokens stay encrypted server-side and never leave clariBI in clear form.
sequenceDiagram
actor U as You
participant C as clariBI
participant V as Pipeboard
U->>C: Click Authorize with Pipeboard
C->>V: Open OAuth authorization
V-->>U: Grant read access?
U->>V: Approve
V-->>C: Authorization code
C->>V: Exchange code for tokens
V-->>C: Access + refresh tokens
C->>C: Encrypt and store credentials
C-->>U: Connection ready
Available tools
clariBI exposes the read-only Pipeboard tools that the vendor's MCP server publishes at connection time. Write operations (create, update, delete, send, refund) are filtered out by a name-pattern blocklist before any tool reaches the analysis engine, so connecting Pipeboard cannot modify data on the vendor side.
The exact tool inventory depends on the Pipeboard features your account has access to. After connecting, try a few natural-language questions to see what Pipeboard data clariBI can pull.
Data flow during analysis
When you ask a question that maps to Pipeboard, the AI engine routes to the right tool, reads the result, and pairs the answer with a chart you can pin to a dashboard.
sequenceDiagram
actor U as You
participant C as clariBI
participant AI as AI engine
participant V as Pipeboard
U->>C: Ask a question about paid-search campaign data
C->>AI: Plan the analysis
AI->>V: Call the right tool
V-->>AI: Tool result
AI->>AI: Summarize and chart
C-->>U: Answer plus visual
Setting up the connection
- Open Data Sources in the clariBI sidebar.
- Click Add data source.
- Open the MCP Servers tab.
- Click the Pipeboard card.
- Click Authorize with Pipeboard.
- Sign in to Pipeboard in the popup window and grant the requested read scopes.
- Back in clariBI, give your data source a name.
- Click Finish.
Permissions and data access
clariBI connects through Pipeboard's OAuth flow and inherits the ad accounts you authorized at Pipeboard. The catalog exposes read tools only (reading campaigns, ad groups, keywords, and performance metrics); clariBI never creates a campaign, changes a budget, or edits a bid through Pipeboard. Disconnect anytime from Settings → Integrations in clariBI, or revoke at Pipeboard.
Troubleshooting
| Error | Cause | Fix |
|---|---|---|
| "No campaigns returned" | The Google Ads account you want is not linked inside Pipeboard, or the connected Pipeboard user cannot see it. | Confirm the account is authorized at Pipeboard and that your user has access, then reconnect. |
| "Spend looks lower than Google Ads UI" | Pipeboard reports the same API figures Google returns, which can lag the UI by a few hours and exclude conversions still being attributed. | Allow for attribution lag and compare against the Google Ads API report rather than the live UI total. |