Agency promptCopy prompt
Replace [variables] Facts ≠ hypotheses Action + follow-up metric
Trusted by marketing teams that talk to data every day
Three steps, from Catchr to your first answer. No code, and nothing to install on your machine.
Meta Ads
3 advertising accounts
Connected
Google Ads
2 advertising accounts
Connected
Google Analytics 4
1 web property
Connected
HubSpot
1 CRM portal
Connected
Open the Catchr MCP entry in the Claude connector directory, add it, then sign in to Catchr and review the access Claude asks for.
Replace account, period, KPI target, and threshold variables before you ask Claude.
Which one fits depends on what you need Claude to do, and on how many sources the question touches.
Compare your options
Sources
Sources
Sources
The data in your file
Connection
Connection
One Catchr workspace
Connection
Upload a CSV or Excel file
Next question
Next question
Query connected sources
Next question
Export again if the scope changes
Catchr gives Claude eight tools, and all eight of them read.
Claude can list the platforms and accounts connected to your workspace, browse the available fields, and run reporting queries against them. That covers spend, delivery, conversions, and creative performance, down to the level you ask for.
Claude cannot create, pause, or edit a campaign, move a budget, publish an ad, or change an audience. There is no write permission to grant, so there is none to supervise.
In Ads Manager. Decide in the conversation what to change and why, then act with the access and the review your team already uses.
Choose your role, open a workflow, then replace the bracketed variables before pasting the prompt into Claude. Every prompt asks for evidence, limits, and a concrete output.
“Why did CPA rise?” sounds simple. The answer is usually buried across exports, formulas, filters, and tabs before the analysis can even start.
Choose the right account, date range, breakdowns, and fields. Then wait for the file and do it again when the question changes.
Rename columns, fix formats, join tabs, and check formulas before you can trust the comparison.
Turn the numbers into a client-ready answer, then repeat the whole process for the inevitable follow-up.
Catchr MCP gives Claude access to the marketing accounts you select, so each follow-up starts with the same marketing context instead of a new manual export.
Clear answers for marketers comparing connectors, data sources, reporting workflows, and dashboard setup.
Claude can analyze returned Google Ad Manager reporting data such as Total revenue, Ad server total revenue, Ad Exchange CPC, Ad Exchange CTR, AdSense CTR, and yield group estimated revenue. It can break results down by fields including Date, Country, Inventory type, and Content source name, subject to the selected network, report compatibility, permissions, and requested period.
Claude can work with Google Ad Manager data at day, week, month, or hour granularity when the requested fields support that breakdown. It can also segment results by dimensions such as country, inventory type, and content source, but incompatible metrics and dimensions should remain in separate analyses.
Yes, when the selected fields and periods are available through Catchr. Claude can compare Total revenue, Ad server revenue, Ad Exchange CPC, or yield group estimated revenue by date, week, month, country, or inventory type; include the network, period, currency context, and comparison target in your prompt.
Claude can identify changes supported by the returned records, such as shifts in CTR or revenue across dates, countries, inventory types, or content sources. Ask it to separate measured observations from possible explanations and to show which fields support each finding.
Effective prompts specify the network, date range, reporting grain, metrics, dimensions, and desired output. For example, ask Claude to compare Total revenue by inventory type, review Ad Exchange CTR by country, or summarize monthly yield group estimated revenue while flagging missing or incompatible fields.
No. The connector exposes directly requestable historical dimensions and metrics included in its checked-in schema. Fields that require custom dimension key IDs or custom field IDs are excluded, and available combinations still depend on Google Ad Manager report compatibility and your permissions.
Yes, when the other sources are also connected and available through Catchr. Before combining results, align dates, currencies, identifiers, account scope, and metric definitions; if a reliable join is not supported, ask Claude for a side-by-side comparison instead.
You need access to the relevant Google Ad Manager network, authorization through Google OAuth, a connected Catchr workspace, and Catchr MCP enabled in Claude. The connection requests identity details and Google Ad Manager access, while the selected network and its permissions determine which reporting data is available.
Claude analyzes the Google Ad Manager records returned through Catchr, not automatically real-time data. Some CTR metrics update nightly, while overall freshness and historical coverage depend on the selected fields, reporting period, network, permissions, and Google Ad Manager API limits. Ask Claude to identify the latest available record date and any missing periods before interpreting trends.
No. This Catchr workflow provides Google Ad Manager reporting data to Claude for analysis and does not give Claude permission to modify the source. Use its findings to prepare recommendations, then apply any changes separately in Google Ad Manager with the appropriate access and review.
Our team is always here to answer any questions you may have about our data connector.
Connect your marketing platforms to Claude with Catchr MCP and start investigating current campaign performance.