MCP App Store
by KeenEthics
Nanga icon

Nanga MCP Server for Claude and ChatGPT

By Spark

Overview

Nanga is the B2B marketing analytics platform built by Spark (Paris), used by e-commerce and lead generation companies to follow their advertising, creative and SEO performance. This connector gives Claude read-only access to your existing Nanga account, for one company chosen when you connect, under your own Nanga permissions. Ask Claude about your advertising: spend, ROAS, CPA and the other metrics your company defines, computed with your own definitions; what moved between two periods and which campaign or platform carries a deterioration; whether data really landed for every platform before you compare; how the account is doing over a period against the previous one; where you stand among comparable companies, anonymously; and what your online store collected next to advertising spend. Claude can also read your saved dashboard analyses and your company context. Figures are computed by Nanga, not by Claude, and every answer carries its dates, units and definitions. A metric Nanga cannot compute for your company is named as such, never shown as a zero. You choose what Claude may read when you connect: company context, recent advertising figures and online store sales are three separate permissions. The connector never writes: it changes no campaign, generates no analysis and creates no account. You can revoke access at any time from your Nanga account or from Claude. An existing Nanga account is required, and your company must have the connector enabled by the Nanga team.

How to connect

  1. Claude: Open the Nanga listing in the Claude connectors directory and choose Connect. Claude listing Nanga exposes 12 tools here.
  2. ChatGPT: Open the Nanga listing in the ChatGPT app directory and choose Connect. ChatGPT listing Nanga exposes 12 tools here.

Tools

compute_paid_metrics

ChatGPT
Computes named paid metrics (spend, roas, cpa, cac, aov, ctr and the like; names are the registry's lowercase keys) over a period, at campaign, adset or ad level, with this company's own metric registry. Returns the rows, the definitions actually applied, and unsupported: the metrics the registry refuses for this company, each with its reason. A refused metric has no value and no substitute, which is not a zero. startDate/endDate are inclusive, at most 90 complete UTC days, ending before today. Optional groupBy (at most 3) and scope narrow the result. Every row also carries the entity of the chosen level, so a groupBy row is that entity's figure and not a total for the group. The requested bounds say what was asked, not what landed; describe_paid_coverage reports what landed.

describe_paid_coverage

ChatGPT
Reports, per advertising platform, whether data really landed over a period: the first and last dates observed, the calendar span between them, the row count and the spend, plus the declared accounts and whether their platform ingested anything. This is what establishes that a period is complete, comparable, or covers every platform; requested bounds alone establish nothing. A platform missing from the answer ingested nothing at all over the period, which is not a platform at zero. observedDaysSpan counts calendar days between the first and last dates, not days carrying data. Declared accounts cover two platforms only (Meta and TikTok), and an account list that could not be read is named in unavailable rather than returned empty. startDate/endDate are inclusive, at most 90 complete UTC days, ending before today.

describe_paid_tables

ChatGPT
Describes the paid advertising data available to this company: without a table, every permitted table with its columns in one answer; with a table, that table alone. Also returns guidance on the company's metrics, the server's current date and, when the server publishes it, availableMetrics: the exact metric names compute_paid_metrics and explain_paid_change accept for this company, some of them French words. An absent availableMetrics means the list was not published, not that the company has no metric. Requires the consent for advertising figures, Performances and Kily permissions, and unrestricted folder access.

explain_paid_change

ChatGPT
Compares a metric over two contiguous windows of equal length (windowDays, 1 to 45), both ending before today, and ranks at most 20 campaigns or platforms by their SIGNED contribution to the observed change. Returns both windows with their exact dates, the metric's unit and definition, and the election of a top driver in topDriverStatus: elected when one entity carries the deterioration (that entity is in topDriver, with volumeShare, its weight among the ranked entities and not a share of the total budget), none_material when worsenings exist but none weighs 5 % of the volume, no_worsening when no entity worsened or disappeared. The election covers deteriorations only. The ranking shows where a change came from; it does not establish why an entity moved. An entity absent from the recent window is returned as disappeared, not as zero. A status of custom_conversion_model means this company counts its online purchases in a model of its own, so this metric is not ranked for it: not computed, which is not an absence of movement. An optional scope (platform, campaignLike, entityIds) narrows the ranking, for example to one platform's campaigns.

get_account_overview

ChatGPT
Returns how the account is doing over a period (startDate/endDate, inclusive, 1 to 45 complete UTC days, ending before today) against the previous period of equal length, which ends the day before it: per advertising platform, spend, roas and cac on both periods with their signed change (delta, and deltaPct as a percentage of the previous value), computed by Nanga with this company's metric registry. roas and cac rest on the conversions each platform attributes to itself. Metrics the registry refuses for this company are named in unsupported; a metric whose conversion event differed between the two periods keeps both values, has no change, and is named in notComparable. A change is null when either period has no value: a platform without data in a period is not a platform at zero, and coverageGaps names the platforms whose data does not span both periods. With the store sales consent, sales adds the store's revenue and orders on both periods, each period with its own status, in an assumed reporting currency; without it, sales is null and withheld names store_sales. A secondary block that could not be read is named in unavailable. Requires the consent for advertising figures, on top of Performances and Kily permissions.

get_company_context

ChatGPT
Reads the company's curated Company Brain: business context, positioning and priorities when available. Uses the same reader as Kily and keeps the connected user's access to shared or internal content. Requires Kily access and the consent for company context. Does not read conversation history or memory notes, retrieve current metrics, or write anything.

get_dashboard_analysis

ChatGPT
Reads the latest saved paid or creative analysis of a dashboard returned by list_dashboards: its findings and recommendations, with the report's own period, generation date and status. It is a stored report, not a fresh calculation. Requires the dashboard's module and Kily access. Does not generate an analysis, query live metrics or change advertising campaigns.

get_peer_benchmark

ChatGPT
Returns this company's position among comparable companies on its advertising metrics, per platform: its own value, its percentile from 0 to 100 among at least five other companies of its comparison group (the company itself excluded), the group's median, and a standing (good, average, poor) read in the metric's direction, a high percentile on a cost being poor. Each metric also carries the spread of its group and flags a small or heterogeneous group, whose percentile is indicative only. Group sizes and other companies' identities are not disclosed. The period is a trailing window (windowDays, snapped to 7, 14, 28, 30, 60 or 90 days, 28 by default) or a finished calendar month (month, YYYY-MM, since 2023-01), returned with the dates actually covered. Metrics refused for this company are named in unsupported, and no_benchmark means no comparison passes the anonymity and freshness rules for that period. An optional platform narrows the answer. Requires the consent for advertising figures, on top of Performances and Kily permissions.

get_sales_overview

ChatGPT
Reads what the company's online store collected over a period: revenue, orders, and the currency those amounts are expressed in, with currencySource, which says that currency is an ASSUMED reporting pivot: the source carries no currency column, the amounts arrive already converted, and the pivot is deduced, not read from the store. Also returns advertising spend, the revenue the platforms attribute to themselves, and the resulting ratios with their definitions. Store revenue and platform attributed revenue measure different things and are not interchangeable. The status separates figures available, no sales over the period, and no e-commerce connector at all: none of the three is a zero. Blended ROAS divides total store revenue by advertising spend alone, so it is not campaign efficiency. Requires the store sales consent, on top of Performances and Kily permissions. The advertising figures belong to the separate consent for advertising figures: without it, spend, platform attributed revenue and every ratio come back empty and withheld names them, which is not an absence of advertising. startDate/endDate are inclusive, at most 90 complete UTC days, ending before today.

list_companies

ChatGPT
Finds the companies the connected Nanga user can access, by name or slug. A remote connection is bound to the company chosen when connecting, so it returns that company only. Pending invitations are excluded, and truncated says the list was cut at the limit.

list_dashboards

ChatGPT
Lists the saved Performances (paid) or Creative dashboards of a company, with their identifiers, within the connected user's module and folder access. Returns dashboard names only, no performance figures; truncated says the list was cut at the limit.

query_paid_data

ChatGPT
Runs one read-only SELECT, written in Snowflake SQL (https://docs.snowflake.com/en/sql-reference), over the tables and columns returned by describe_paid_tables, through Kily's protected warehouse reader, which enforces this company and the requested dates on every table. startDate/endDate are inclusive, at most 90 complete UTC days, ending before today. Returns at most 500 rows, and truncated says the result was cut. The requested bounds are no proof that data covers them, and a missing row or a null metric is not a zero. Does not read platform APIs or generate a saved analysis.

compute_paid_metrics

Claude

describe_paid_coverage

Claude

describe_paid_tables

Claude

explain_paid_change

Claude

get_account_overview

Claude

get_company_context

Claude

get_dashboard_analysis

Claude

get_peer_benchmark

Claude

get_sales_overview

Claude

list_companies

Claude

list_dashboards

Claude

query_paid_data

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/nanga"><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/nanga)