MCP App Store
by KeenEthics
Paramark icon

Paramark MCP Server for Claude and ChatGPT

By Paramark

Overview

The Paramark connector brings your Paramark data into Claude, so you can put it to work elsewhere: building presentations, drafting messages, or combining it with other data and workflows. - Marketing Mix Modeling (MMM) results: what each channel contributed, cost per incremental outcome, and incremental return on ad spend for any published report, by week, month or quarter. - Paramark Live MMM: how channels are trending since your last published report, through the most recent data. - Experiments: what a geo test was designed to detect, and the lift it measured. - The data behind the models: spend and impressions by channel, and your target metrics over time.

How to connect

  1. Claude: Open the Paramark listing in the Claude connectors directory and choose Connect. Claude listing Paramark exposes 11 tools here.
  2. ChatGPT: Open the Paramark listing in the ChatGPT app directory and choose Connect. ChatGPT listing Paramark exposes 11 tools here.

Tools

get_experiment_design

ChatGPT
One experiment design: per target metric, the power curve giving the probability the experiment would detect a causal effect at each lift, and the threshold the design was read against.

get_experiment_results

ChatGPT
One experiment's results: per test cell its test locations, the channel tested and, per target metric, the treatment window and control markets; plus measured_impact, the absolute lift on the target and the spend in test locations per published run.

get_live_mmm_output_since_refresh

ChatGPT
The latest nightly (Live MMM) run's output for an MMM: incremental contribution to the target (incremental, in the target's units), spend and efficiency per channel and per period, through the most recent data. data is column-oriented, one row per channel (plus baseline) per period, and holds only the periods after source_data_end — the part a nightly run adds beyond the published refresh. For the full history use get_mmm_report on the MMM.

get_media_data

ChatGPT
Spend and impressions per channel over a window — the raw inputs the MMM is fitted on, as reported, with no modelled ratios. Every channel's spend and impressions series is aligned to the response's periods; spend_total / impressions_total cover the whole window. meta.currency names the currency. A null value is a gap, not a zero. in_model says whether the customer's MMMs fit the channel.

get_mmm_report

ChatGPT
One MMM report's data, as the dashboard renders it: the newest published report by default, or the refresh you name. metadata names the target metric, the channels and the fitted window. channels_data has incremental contribution to the target (incremental, in the target's units), spend and efficiency per channel per period; total_data sums every channel and baseline per period beside the measured actual; summary_data is channels_data over the summary window.

get_target_metrics_data

ChatGPT
Every target metric in the dataset (signups, revenue, ...) as account-level volume per period on one shared timeline — never attributed to channels here; that is what the MMM output is for. Takes the same window arguments as get_media_data.

list_experiment_designs

ChatGPT
The experiment designs with a published report the caller may view, newest first. experiment_design_id is what get_experiment_design takes.

list_experiment_results

ChatGPT
The experiments with published results the caller may view, newest first. experiment_id is what get_experiment_results takes.

list_mmm_reports

ChatGPT
The published reports of one MMM the caller may view, newest first, each with the refresh month and year it covers and a report_url to open it. get_mmm_report reads one by its refresh month and year.

list_mmms

ChatGPT
The customer's marketing mix models. id is the mmm_id the other MMM tools take. has_daily_mmm_data says whether get_live_mmm_output_since_refresh has a nightly run to return.

whoami

ChatGPT
The signed-in user's email and the customer their token is scoped to. Call this first to confirm the connection works; every other tool reads this customer's data.

get_experiment_design

Claude

get_experiment_results

Claude

get_live_mmm_output_since_refresh

Claude

get_media_data

Claude

get_mmm_report

Claude

get_target_metrics_data

Claude

list_experiment_designs

Claude

list_experiment_results

Claude

list_mmm_reports

Claude

list_mmms

Claude

whoami

Claude

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/paramark"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/paramark)