MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
🔌 Exposes Comprehensive customer churn prediction and retention analytics.
npm MIT -
@retentioncheck/mcp-servergithub.com/brianfofficial/retentioncheck-v2updated this year
MCP server for AI-powered churn analysis. Analyze cancellation feedback to identify churn patterns and get actionable recommendations.
npm MIT -
RetainQ MCP Server — Connect AI assistants to your churn reduction platform. Query retention metrics, manage flows/offers, analyze customer data, and run AI churn analysis.
npm MIT -
@vic08/mcp-stripe-bigithub.com/vic08/mcp-stripe-biupdated this year
Stripe Business Intelligence MCP server — MRR, churn, cohorts, LTV, and SaaS revenue analytics
npm MIT -
stripe-insightsupdated this year
Stripe Revenue Intelligence for AI Agents — MRR, churn, forecasts, and customer insights via MCP.
npm MIT -
MCP server for Stripe analytics — revenue, customers, subscriptions, refunds, and churn metrics from Claude.
npm MIT -
MCP server for CodeDelta — deterministic code-churn measurement and AI-agent detection, callable by AI agents (Claude Code, Cursor, etc.)
MIT -
stripe-analytics-mcpgithub.com/npow/stripe-analytics-mcpupdated this year
30-second Stripe morning check via MCP: MRR, churn, failed payments, and trial risk.
MIT -
Enterprise customer-retention intelligence for Archestra—deterministic churn ML over MCP with human-approved rescue workflows.
MIT ★ 1 -
Free read-only MCP playbook for client retention, renewals, QBRs and churn risk — built for devs and agency founders.Free account management playbook for B2B agencies: plans, churn risk, renewals, meeting prep.
MIT ★ 1 -
windback-mcpgithub.com/windback-ai/mcpupdated this year
Official Windback MCP server — query your churn data and trigger recovery actions from Claude Desktop, Cursor, and any MCP-compatible AI client.
npm MIT -
Churnsolution-MCPgithub.com/Churnsolution/Churnsolution-MCPupdated this year
Official MCP server for Churn Solution — read-only access to subscription retention analytics: cancellation flows, failed payment recovery, and customer feedback.
MIT -
Per-user retention agent for subscription apps. Reads cross-source signals (RevenueCat, Stripe, Sentry, PostHog) via MCP, scores per-user churn risk, drafts personalized retention plays + engineering stabilization tickets.
MIT -
@firstdistro/mcpactive
FirstDistro MCP server — manage customer health, churn risk, and journeys from Claude, Cursor, and other AI tools
npm MIT -
saas-brain-mcpgithub.com/Mohd16kaif/saas-brain-mcpupdated this year
Open-source MCP server for Claude AI with Stripe and Supabase integration for SaaS analytics, churn analysis, subscription tracking, and revenue insights using natural language
-
dotplot-mcpgithub.com/brownglasses/dotplot-mcpupdated this year
Product analytics MCP server for early-stage startups: user behavior analysis, dot plots, aha moment discovery, retention curves, onboarding funnels, churn analysis — YC methodology, works with Claude Code & Cursor
pypi MIT ★ 1 -
Production-ready Customer Success MCP Server - Complete RevOps platform for customer health scoring, churn prediction, onboarding automation, and retention management. Built with FastMCP, PostgreSQL, Redis, and integrates with Zendesk, Intercom, Mixpanel, and SendGrid.
★ 1 -
stripe-founder-mcpgithub.com/PrimeEcto/stripe-founder-mcpupdated this year
An opinionated read-only Stripe MCP server for indie SaaS founders to ask AI about MRR, churn, failed payments, dunning recovery, disputes, at-risk customers, and support context in plain English.
MIT ★ 1 -
Customer Retention LTVno update data
Customer LTV, churn risk, repurchase, lifecycle email, and winback intelligence.
pypi -
mcp-servergithub.com/retain-so/mcp-serverupdated this year
Model Context Protocol server for Retain: let AI agents query churn risk and act on retention.
npm MIT ★ 1 -
QA Radargithub.com/muratkus/qaradarno update data
Tells AI agents which files to test first — churn, coverage, and test mapping as risk scores.
pypi -
MCP server for streaming platform analytics with PostgreSQL - supports engagement tracking, churn analysis, funnel metrics, and cohort analysis
-
revenue-mcpgithub.com/warfare-hub/revenue-mcpupdated this year
Revenue Dashboard MCP — query your MRR, churn, and revenue from Stripe, Gumroad, Lemon Squeezy, Paddle & Polar directly in Claude
npm -
Governed AI-ops for redis + rabbitmq: memory-pressure/latency/queue-backlog/connection-churn RCAs, s
pypi MIT -
mcp-customer-servicegithub.com/zavora-ai/mcp-customer-serviceupdated this year
Customer Service MCP Server — conversations, customer intelligence, resolution, routing, satisfaction, and churn prediction for AI agents
cargo Apache-2.0 -
MCP server for RevenueCat Charts API — ask your AI agent about MRR, churn, revenue, and more
npm MIT -
Read-only MCP server for Stripe revenue analytics: MRR, churn, failed payments. Includes a keyless demo mode
MIT -
churnlensgithub.com/cognis-digital/churnlensupdated this year
Self-hosted SaaS metrics — MRR, churn, LTV from Stripe or CSV
NOASSERTION -
Zero-dependency Model Context Protocol (MCP) server for deep Git archaeology, churn hotspots, and co-change analysis
MIT -
MCP server for Tools4Skool: manage your Skool community (members, churn risk, analytics, DMs) from Claude, Cursor and other MCP clients
MIT -
Git analytics MCP server: 8 tools for repo overview, author stats, branch health, file hotspots, commit frequency and code churn
-
Local read-only MCP tools for Git repository archaeology, churn, hotspots, and hygiene. Tools include repository summary, recent changes, file hotspots
npm MIT -
MCP server for git archaeology - churn hotspots, blame summaries, bus factor, commit forensics and file history over any local repository
MIT ★ 3 -
adtivity-mcpupdated this year
Adtivity MCP server — install Adtivity analytics, session replay, error tracking and churn prediction into any codebase via Claude Code or Cursor in under 10 minutes
npm MIT -
growth-mcpgithub.com/thaolst/growth-mcpupdated this year
MCP server for growth marketing - campaign design, retention analysis, churn prediction, A/B testing
MIT ★ 10 -
agentlio-market-intel-mcpgithub.com/agentlio/agentlio-market-intel-mcpupdated this year
Production-ready MCP server for Google Play & App Store review intelligence: sentiment, benchmarking, churn signals, and growth actions.
-
stripe-founder-mcpupdated this year
The Stripe co-pilot for indie SaaS founders. Ask your AI about MRR, churn, failed payments, and at-risk customers via MCP.
npm MIT -
Per-function CRAP scores from complexity and coverage, churn-ranked worklists, and ratchet gates for code changes. CLI, MCP, and GitHub Action.
pypi MIT ★ 1 -
shopify-partner-agentgithub.com/rushikeshmore/shopify-partner-agentupdated this year
MCP server for Shopify Partner API analytics - 25 tools for MRR, churn, retention, merchant health, forecasting. Free and open source.
pypi MIT ★ 14 -
schema-sentinelgithub.com/ramoniglesias98/schema-sentinelupdated this year
Read-only MCP server that hands an AI agent a Postgres schema, its ERD, missing indexes, circular FKs, migration risk and per-table git churn.
AGPL-3.0 -
A V8 deoptimization toolkit for AI agents and dev workflows: MCP server, findings engine, benchmark harness, and fix-verify comparison for inline caches, deopts, and hidden-class churn
npm MIT -
Find TODO/FIXME/HACK markers across a repo with their real age and author from git blame, over MCP. Comment-aware (ignores markers in strings and URLs), stale-vs-hot split, debt x churn hotspots. Read-only.
MIT -
🔌 Exposes Customer relationship management toolkit: lead scoring, deal stage prediction, follow-up scheduling, customer health scoring, and churn prediction. By MEOK AI Labs.
pypi MIT -
A line check for hospitality operators' Xero books. Deterministic anomaly detection over 36 months of live data — duplicate payments, cost drift, wage-ratio creep, customer churn — with a Claude layer for plain-English narrative, drafted chase emails, and a live agent over the Xero API + Remote MCP server. No LLM in the detection loop.
MIT -
A Git intelligence MCP server built with Node.js and TypeScript that analyzes local Git repositories to surface insights like hotspots, churn, temporal coupling, knowledge maps, and risk scoring. Designed for AI agents, it exposes repository analytics tools through the Model Context Protocol (MCP) while keeping all data local and read-only.
MIT ★ 12 -
luca-assistantgithub.com/troyt-666/luca-assistantupdated this year
Credit card optimization MCP server for Claude Code (撸卡助手)
pypi MIT -
telco-mcp-servergithub.com/rashad-malik/telco-mcp-serverupdated this year
This project demonstrates how to build an MCP server that bridges AI assistants with data analysis and machine learning capabilities.
-
MCP server for the GASP Standard: SaaS metrics definitions, formulas, benchmarks, entity relationships, business model graph, access governance, and query generation
npm Apache-2.0 -
AbandonAlpha — Failed-Payment & Checkout Drop-Off Recovery. Free interactive benchmark, live SVG badges, OpenAPI 3.1 & MCP Server: https://www.abandonalpha.com
-
Find customers who stopped buying from an orders CSV: at-risk and lost customers, revenue at risk and repeat rate. Local, no uploads. Go MCP server and CLI.
npm MIT