ChurnLens

io.github.kindrat86Published by GitHub account kindrat86v1.0.1Updated Oct 24, 2026

Buyer-side SaaS due-diligence maths: NRR, GRR, revenue concentration, zombie MRR, LTV:CAC.

VerifiedStreamable HTTPWeb executableFinanceData & Analytics

Overview

AI-generated overview

A remote MCP server that computes SaaS due-diligence metrics — NRR, GRR, revenue concentration, zombie MRR, LTV:CAC and a health score — from figures you supply

What you can do
Calculate retention and churn: NRR, GRR, revenue churn, annualised churn and the NRR-minus-GRR spread from one period's MRR movements, plus gross-margin-adjusted LTV, LTV:CAC and CAC payback in months. Assess revenue concentration with the Herfindahl-Hirschman Index, top-N share and whale detection. Flag dormant-but-paying accounts and the ARR at risk behind them. Score a SaaS business 0-100 across retention, growth, concentration, efficiency and durability, and return the scoring thresholds with their provenance. Results come back as structured content alongside text.
When to use it
Useful for acquirers, private-equity and M&A analysts, or founders doing a first-pass screen of a SaaS business's retention, concentration and unit economics from summary figures. Not a substitute for customer-level cohort or renewal analysis.
Requirements
A remote streamable HTTP endpoint; no account, authentication, API key or rate limit is declared. Clients that only speak stdio can reach it through the mcp-remote bridge, which needs Node.js via npx.
Before you install
The tools only compute from figures you supply and are described as a first-pass screen, not a substitute for customer-level data. Scoring bands are thresholds informed by published benchmarks, not measured survey data, and segment matters. The README states nothing sent is stored, but the figures leave your machine to a third-party endpoint.

Installation

In SourceWeft

  1. Open ChurnLens in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.kindrat86%2Fchurnlens/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "churnlens": {
      "type": "http",
      "url": "https://churnlens.site/api/mcp"
    }
  }
}

README

ChurnLens MCP server

Buyer-side SaaS due-diligence maths for AI agents. Net and gross revenue retention, revenue concentration risk, dormant ("zombie") MRR, LTV:CAC and a composite health score — computed from figures you supply.

Live endpoint: https://churnlens.site/api/mcp — streamable HTTP, MCP protocol 2024-11-05. No authentication, no account, no rate limit, and nothing you send is stored.

Install

Claude Desktop, Claude Code, or any client that speaks stdio:

bash
npx mcp-remote https://churnlens.site/api/mcp

By config:

json
{  "mcpServers": {    "churnlens": {      "command": "npx",      "args": ["mcp-remote", "https://churnlens.site/api/mcp"]    }  }}

A GET on the endpoint returns the manifest. The machine-readable descriptor is at /.well-known/mcp.json.

Tools

ToolWhat it returns
calculate_churn_rateNRR, GRR, revenue churn, correctly compounded annualised churn, and the NRR−GRR spread that exposes churn masked by expansion
analyze_revenue_concentrationHerfindahl-Hirschman Index, top-N revenue share, and which customers are large enough that losing one is a balance-sheet event
detect_zombie_mrrAccounts still paying but dormant past a threshold, and the ARR at risk behind them
score_saas_healthComposite 0–100 across retention, growth, concentration, efficiency and durability, plus the weakest dimension
calculate_ltvGross-margin-adjusted lifetime value, LTV:CAC and CAC payback in months
get_scoring_bandsEvery threshold the tools apply, with its provenance

Every tool returns structuredContent alongside the text block, so an agent gets typed numbers rather than prose it has to parse back out.

Example

js
calculate_churn_rate({  starting_mrr:    100000,  expansion_mrr:    37000,  contraction_mrr:   5000,  churned_mrr:      17000})
// nrr_pct: 115, grr_pct: 78, expansion_masking_spread_pts: 37// "A wide NRR-GRR spread: expansion revenue is masking substantial//  churn underneath. Diligence should look at the retained base//  separately from upsell."

A business reporting 115% net revenue retention sounds excellent. The same business at 78% gross revenue retention is losing nearly a quarter of its revenue base a year and covering the hole with upsell. Most dashboards show the first number and not the second.

On the scoring bands

get_scoring_bands returns thresholds, not measured data. They are informed by published industry benchmarks — SaaS Capital, Benchmarkit, Recurly and FE International — cited with sources at churnlens.site/benchmarks. Segment matters enormously: median retention for enterprise infrastructure and for SMB self-serve are not the same number. Do not present a band as though it were a survey result.

What it does not do

These tools compute from summary figures you supply. They cannot see what only emerges from customer-level data — cohort decay curves, renewal-cliff timing, concentration in specific logos. Treat them as a first-pass screen.

Verify the maths yourself

The same calculations are open source under MIT at kindrat86/saas-metrics — zero dependencies, every scoring band documented, 27 tests. A result from this server can be reproduced independently.

Interactive versions for humans, no signup: churnlens.site/free.

About

ChurnLens is a buyer-side SaaS due-diligence tool for acquirers, private-equity firms and M&A analysts.

Unaffiliated with the similarly named churnlens.io (retention automation) or churnlens.tech (churn prediction).

MIT licensed. Free.

Source: README.md at commit 6b80333

Tools

6

calculate_churn_rate

Calculate net revenue retention (NRR), gross revenue retention (GRR), revenue churn and implied customer lifetime from one period's MRR movements. Also reports the NRR-minus-GRR spread, which reveals how much churn is being masked by expansion revenue.

Parameterschurned_mrrstarting_mrrrequiredexpansion_mrrcontraction_mrr

analyze_revenue_concentration

Assess customer concentration risk across a book of revenue using the Herfindahl-Hirschman Index (HHI), top-N share and whale detection. Answers the question every acquirer asks first: how much revenue walks out with one logo?

Parameterstop_ncustomer_mrrsrequiredwhale_threshold_pct

detect_zombie_mrr

Identify dormant-but-paying accounts — revenue that still counts in MRR but whose customers have stopped showing up. Zombie revenue is one renewal notice from cancelling and is invisible to standard revenue dashboards.

Parametersaccountsrequiredthreshold_days

score_saas_health

Score a SaaS business 0-100 across five dimensions — retention, growth, concentration, efficiency and durability — and return the composite. Every mapping is published, so the score can be reconstructed by hand.

Parametersnrr_pctrequiredltv_to_cac_ratiorequiredannual_plan_share_pctrequiredmonthly_churn_rate_pctrequiredtop_customer_share_pctrequired

calculate_ltv

Calculate gross-margin-adjusted customer lifetime value, the LTV:CAC ratio and CAC payback in months. Omitting gross margin yields lifetime revenue rather than lifetime value — usually a third of the number.

Parameterscacarparequiredgross_margin_pctmonthly_churn_rate_pctrequired

get_scoring_bands

Return the scoring thresholds ChurnLens applies to NRR, revenue concentration and the composite health score. These are bands, not measured benchmark data — the sourced benchmark figures are cited at https://churnlens.site/benchmarks.

Parametersmetric

Version history

1
  1. v1.0.1LatestSep 16, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts