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 connected Adalyser reporting data using 43 metrics and 34 dimensions. Representative fields include Sales Value, Lead Sale Conv Rate, CPL, Avg Sales Value, Channel, Product, Platform, Client Name, Market, and Week Start. Exact availability depends on the returned report, selected client or campaign, permissions, and requested period.
Claude can break down returned Adalyser results by fields such as client, product, ad group, channel, platform, market, break position, campaign type, and broadcast week. The available detail depends on the report and compatible fields, so specify the required grain and ask Claude to state any limitations before calculating totals or rates.
Yes, when the required Adalyser records are available for both periods. Claude can compare measures such as Sales Value, Avg Sales Value, Lead Sale Conv Rate, and CPL by dimensions including Week Start, Product, Channel, Platform, or Market. Include the periods, comparison criteria, and reporting grain in your prompt.
Claude can identify patterns in returned Adalyser data, such as changes in sales value, conversion rate, or cost per lead across products, ad groups, channels, platforms, and weeks. It should present unusual movements as observations rather than proven causes and identify what you should validate next.
Use prompts that name the client or campaign scope, period, comparison, fields, threshold, and desired output. For example, ask Claude to compare weekly Sales Value by Channel, review CPL by desktop and mobile sources, or summarize new-user versus returning-user sales value for a client report.
Yes, when the other sources are also connected through Catchr and provide compatible data. Align dates, client scope, identifiers, currencies, attribution definitions, and reporting grain before combining results. If a reliable join is not supported, ask Claude for a side-by-side comparison instead.
Yes, provided the relevant records are available through the Catchr connection. Claude can compare clients using Client Id or Client Name and segment campaign activity by Product, Ad Group, Channel, Platform, or Market. Request separate results before a combined summary to avoid hiding differences in scope or definitions.
You need your Adalyser username and password, access to the relevant Adalyser data, a Catchr workspace with Adalyser connected, and Catchr MCP enabled in Claude. Available clients, campaigns, report families, and fields depend on the connection and your Adalyser permissions.
Claude analyzes the Adalyser records returned through Catchr and should not assume they are real time. Freshness and historical coverage can vary by report, selected period, client, campaign, field, and upstream limits. Ask Claude to state the latest record date and flag missing intervals before interpreting trends.
No. Catchr provides Adalyser data to Claude for analysis and does not grant permission to edit campaigns, change settings, or update source records. Use Claude's findings to prepare recommendations, then review and apply any operational changes in Adalyser with the appropriate access.
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.