[{"_1":2,"_3":-5,"_4":-5},"loaderData",{"_5":6,"_7":8,"_9":10},"actionData","errors","root",{"_131":132},"routes/modules.$creator.$moduleId",{"_14":15,"_16":17,"_18":19,"_20":21},"routes/modules.$creator.$moduleId.endpoints",{"_11":12,"_13":-5},"error","Module not found","tools","module",{"_20":22,"_23":24,"_25":26,"_27":28,"_29":30,"_31":32,"_33":34,"_35":26,"_36":37,"_38":-5,"_39":-5,"_40":41,"_42":43,"_44":45,"_46":47,"_48":49,"_50":51,"_52":53,"_54":55,"_56":-5,"_57":49,"_58":59,"_60":61,"_62":63,"_64":65,"_66":67,"_68":69,"_70":71,"_72":73,"_74":75,"_76":77,"_78":79,"_80":-5,"_81":-5,"_82":-5,"_83":49,"_84":-5,"_85":86,"_87":88,"_89":90,"_91":92,"_93":94,"_95":96},"apiUrl","https://odel.app/api","creator","embeddedlayers","moduleId","mcp-analytics","@embeddedlayers/mcp-analytics","displayName","mcp analytics","tagline","The statistical analyst in your AI chat — validated, citable, re-runnable analysis of your data.","iconKey","https://avatars.githubusercontent.com/u/153229593?v=4","category","remote","status","published","visibility","public","metaDescription","deploymentType","external","workerName","bindingName","mcpConfig","{\"url\":\"https://api.mcpanalytics.ai/auth0\",\"transport\":\"streamable-http\",\"authType\":\"none\"}","pricingModel","free","creatorUserId","system:external-import","createdAt",1781363197000,"updatedAt",1788409132000,"sourceRegistry","official-mcp-registry","sourceUrl","https://registry.modelcontextprotocol.io/v0/servers?search=ai.mcpanalytics%2Fanalytics","sourceVerified",false,"sourceMissingSince","importedAt","upstreamStars",7,"upstreamUpdatedAt",1787581731000,"detectedTransport","streamable-http","detectedAuthType","oauth","probeStatus","ok","lastProbedAt",1787717916000,"githubRepoUrl","https://github.com/embeddedlayers/mcp-analytics","githubRepoFullName","embeddedlayers/mcp-analytics","releaseId","ext-embeddedlayers-mcp-analytics","version","1.0.7","descriptionMarkdown","# MCP Analytics Suite\n\n**The statistical analyst in your AI chat.** Bring a CSV (or connect a live source) and a question. A standing team of specialist agents builds a custom analysis specific to your data, validates the methodology, and ships back a citable, interactive report. The analysis is **yours** — it lives in your library, reruns on fresh data for a fraction of the creation cost, and is queryable from Claude, Cursor, or any MCP client. The work compounds.\n\n> **This is the public listing and documentation repository.** Issues, feature requests, and examples live here. The API server code is maintained separately.\n\n[Sample Reports →](https://mcpanalytics.ai/case-studies) • [Try Demo →](https://mcpanalytics.ai/demo) • [Pricing →](https://mcpanalytics.ai/pricing)\n\n**Try it before installing anything.** The [free tools](https://mcpanalytics.ai/free/) run in the browser on a CSV you upload — no account, no key, no MCP client. Each one is a real analysis with the method written out: [PCA](https://mcpanalytics.ai/free/standard_pca), [correlation](https://mcpanalytics.ai/free/standard_correlation), [forecasting](https://mcpanalytics.ai/free/standard_forecasting), [RFM segmentation](https://mcpanalytics.ai/free/standard_rfm), [regression (GLM)](https://mcpanalytics.ai/free/standard_glm).\n\n

\n\n[![Glama Score](https://glama.ai/mcp/servers/embeddedlayers/mcp-analytics/badges/score.svg)](https://glama.ai/mcp/servers/embeddedlayers/mcp-analytics)\n[![npm](https://img.shields.io/npm/v/@mcp-analytics/mcp-analytics)](https://www.npmjs.com/package/@mcp-analytics/mcp-analytics)\n[![License](https://img.shields.io/badge/License-MIT-green)](LICENSE)\n[![Platform](https://img.shields.io/badge/Platform-MCP_Compatible-blue)](https://mcpanalytics.ai/install)\n[![Docs](https://img.shields.io/badge/Docs-mcpanalytics.ai-brightgreen)](https://mcpanalytics.ai/docs)\n\n**Hire the team. Own the analysis. Rerun forever.**\n\n[🚀 Quick Start](#quick-start) • [🔄 How It Works](#how-it-works) • [🛠️ MCP Tools](#mcp-tools) • [🛡️ Security](#security--compliance) • [📖 Documentation](#documentation)\n\n

\n\n

\n\n[![Demo Video](https://raw.githubusercontent.com/embeddedlayers/mcp-analytics/main/assets/demo-preview.png)](https://github.com/embeddedlayers/mcp-analytics/releases/download/v1.0.4/demo.mp4)\n\n*Click to watch: Ask a question → upload data → get an interactive report with AI insights*\n\n

\n\n---\n\n## Overview\n\nYou bring data and a question. A pipeline of specialist agents — spec drafter, builder, verifier, fixer, deployer — turns your question into a custom analysis for your data. The result is an interactive report: charts, AI-narrated insights, exportable PDF, embedded source code, citable. Every commissioned analysis joins your private library — query it from any MCP client, rerun on fresh data with one call, share with collaborators on your terms.\n\n**Cornerstone modules** ship pre-built (t-tests, regression, churn, segmentation, forecasting, customer LTV, A/B testing, time series, survival analysis, and more) so you can see a finished report in under a minute and verify the team can build things that work. **Custom analysis creation** is the named revenue event — pay once to build the capability, own it, rerun for a fraction of the creation price. A build that fails is never billed.\n\nConnect data however it lives: CSV upload, public URL, or live OAuth connectors for Google Analytics 4 and Google Search Console (more coming). Once a connector is linked, every rerun pulls fresh data automatically — no re-export step.\n\n### Choose Your Depth — Four Tiers\n\nEvery analysis runs through the same validated pipeline — you choose how far it goes:\n\n| Tier | What you get | Time |\n|------|-------------|------|\n| **Snapshot** | One chart and a verified insight — an instant read of your data, covered by your welcome credits | ~2 min |\n| **JSON** | One computed statistical answer — the numbers and the method — deployed as a tool you re-run on fresh data | ~5 min |\n| **Brief** | The computed answer, presented — chart, key figures, and method on a single shareable page | ~7 min |\n| **Deck** | The full study — a complete statistical report built to your brief and independently verified; a durable module you own and re-run forever | 30–45 min |\n\nMore rigor outranks more charts: going deeper buys real statistical methods — hypothesis tests, regression, diagnostics — not just more cards. You pay for depth, and only if the build succeeds. [How the tiers work →](https://mcpanalytics.ai/tiers)\n\n### Why MCP Analytics\n\n- **Citable** — APA / MLA / Chicago / BibTeX in one click, ready for papers, decks, and regulatory filings\n- **Sourceable** — R source code embedded in every report; a skeptical reader can run it and get the same answer\n- **Reproducible** — fixed seeds, Docker isolation, validated methods; same input → same output, forever\n- **Yours** — every commissioned module is private to your account; rerun on fresh data, query across your portfolio\n- **MCP-native** — query the library from Claude, Cursor, Windsurf, or any MCP client\n- **Secure** — OAuth2, encryption at rest, isolated container processing per analysis\n- **Honest** — when an analysis has issues, the team gives you a free re-run; the relationship is built on the report being right\n\n## Quick Start\n\n### 1. Get an API Key\n\nSign up free at [account.mcpanalytics.ai](https://account.mcpanalytics.ai), go to account settings, and copy your API key (starts with `mcp_`). You get **500 welcome credits** — no credit card required. That covers a one-page Brief, or a couple of instant Snapshots.\n\n### 2. Connect\n\nThree options — all connect to the same platform with the same tools.\n\n#### Option A: npx Install (Recommended)\n\nWorks with Claude Desktop, Cursor, Windsurf, and any stdio MCP client. Requires Node.js 18+.\n\n**Claude Desktop** — add to `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) or `%APPDATA%\\Claude\\claude_desktop_config.json` (Windows):\n\n```json\n{\n \"mcpServers\": {\n \"mcpanalytics\": {\n \"command\": \"npx\",\n \"args\": [\"-y\", \"@mcp-analytics/mcp-analytics\"],\n \"env\": {\n \"MCP_ANALYTICS_API_KEY\": \"mcp_your_key_here\"\n }\n }\n }\n}\n```\n\n**Cursor / Windsurf** — add to `.cursor/mcp.json`:\n\n```json\n{\n \"mcpServers\": {\n \"mcpanalytics\": {\n \"command\": \"npx\",\n \"args\": [\"-y\", \"@mcp-analytics/mcp-analytics\"],\n \"env\": {\n \"MCP_ANALYTICS_API_KEY\": \"mcp_your_key_here\"\n }\n }\n }\n}\n```\n\n**Claude Code** — run in your terminal:\n\n```bash\nclaude mcp add mcpanalytics -- npx -y @mcp-analytics/mcp-analytics\n# Then set MCP_ANALYTICS_API_KEY in your environment\n```\n\n#### Option B: Direct API Key (No npm)\n\nFor MCP clients that support Streamable HTTP transport with custom headers:\n\n```json\n{\n \"mcpServers\": {\n \"mcpanalytics\": {\n \"url\": \"https://api.mcpanalytics.ai/mcp/api-key\",\n \"headers\": {\n \"X-API-Key\": \"mcp_your_key_here\"\n }\n }\n }\n}\n```\n\n#### Option C: OAuth2 (No API Key)\n\nZero-config — a browser opens for login on first connection:\n\n```json\n{\n \"mcpServers\": {\n \"mcpanalytics\": {\n \"url\": \"https://api.mcpanalytics.ai/auth0\"\n }\n }\n}\n```\n\n#### Browse Tools First (No Account Needed)\n\nExplore the full tool catalog before signing up:\n\n```bash\n# Static metadata (tool names, descriptions, all transport options)\ncurl https://api.mcpanalytics.ai/.well-known/mcp.json\n\n# MCP protocol discovery (no auth — works with any MCP client)\ncurl -X POST https://api.mcpanalytics.ai/mcp/discover \\\n -H 'Content-Type: application/json' \\\n -d '{\"jsonrpc\":\"2.0\",\"method\":\"tools/list\",\"id\":1,\"params\":{}}'\n```\n\n### 3. Start Analyzing\n\nRestart your MCP client. Ask:\n\n- *\"Upload sales.csv and find what drives revenue\"*\n- *\"What statistical test should I use for this survey data?\"*\n- *\"Forecast next quarter's sales from this time series\"*\n\n## How It Works\n\n### The MCP Analytics Workflow\n\n1. **Upload your data** — `datasets_upload` securely processes your CSV (or reuse an existing dataset / connected source)\n2. **Commission the analysis** — `create_analysis` takes your question in plain language, your dataset, and the tier you choose (snapshot, json, brief, or deck)\n3. **Watch it build** — `build_status` reports progress, queue position, and the report link when done\n4. **Get the report** — `reports_view` delivers the interactive report; `report_cards` displays individual cards inline\n5. **Rerun forever** — `run_analysis` re-runs any analysis you own on fresh data for a fraction of the creation cost\n\n```\nUser: \"What drives our sales growth?\"\nMCP Analytics:\n → Scopes the right statistical method for your data's shape\n → Writes validated R in an isolated container — deterministic, fixed seeds\n → Runs it, then independently verifies numbers and narrative\n → Returns a citable, interactive report you own\n```\n\n## MCP Tools\n\nThe platform provides a complete suite of MCP tools for end-to-end analytics:\n\n### Analysis\n- **`create_analysis`** - Commission a new analysis from a plain-language question, at the tier you choose\n- **`build_status`** - Track a build: stage progress, queue position, report link\n- **`run_analysis`** - Run an analysis you own (or one discovered via `discover_tools`) on fresh data\n- **`modify_analysis`** - Turn an existing analysis into a new version — reword the question, change the framing\n\n### Discovery\n- **`discover_tools`** - Browse what you can run: your commissioned analyses plus the prebuilt library\n- **`tools_schema`** - Get an analysis's parameter schema — always call this before `run_analysis`\n\n### Data Management\n- **`datasets_upload`** - Secure data upload with encryption\n- **`datasets_list`** - List and search your uploaded datasets\n\n### Connectors\n- **`connectors_list`** - List available data source connections\n- **`connectors_query`** - Pull live data from a connected source\n\n### Reporting & Insights\n- **`reports_view`** - Get a shareable browser link for a report\n- **`reports_list`** - Your report library — every analysis delivered, searchable in plain language\n- **`report_cards`** - Browse a delivered report's individual cards (charts, tables, insights)\n- **`ask_library`** - Ask one question across *all* your delivered analyses; get a synthesized answer with citations back to each source report\n- **`agent_advisor`** - AI help desk — which analysis fits your question, and how to read the result\n\n### Platform Tools\n- **`billing`** - Usage and credit management\n- **`account_link`** - Link to the right account page for anything not doable in chat\n- **`about`** - Platform documentation and info — how it works, tiers, usage\n\n> Browse the catalog yourself, without an account:\n> `curl -X POST https://api.mcpanalytics.ai/mcp/discover -H 'Content-Type: application/json' -d '{\"jsonrpc\":\"2.0\",\"method\":\"tools/list\",\"id\":1,\"params\":{}}'`\n> Discovery returns the 15 tools that work pre-auth; `billing`, `connectors_list`,\n> and `connectors_query` appear once you connect with a key or via OAuth.\n\n## Features\n\n### Natural Language Interface\n\nJust describe what you need:\n\n```\n\"What drives our revenue growth?\"\n\"Find customer segments in our data\"\n\"Forecast next quarter's sales\"\n\"Did our marketing campaign work?\"\n```\n\n### Comprehensive Analysis Suite\n\n\n\n\n\n\n\n\n\n\n

\n\nStatistical Methods\n- Regression Analysis\n- Advanced Modeling\n- Hypothesis Testing\n- Survival Analysis\n- Bayesian Methods\n\n	\n\nMachine Learning\n- Ensemble Methods\n- Boosting Algorithms\n- Neural Networks\n- Clustering\n- Dimensionality Reduction\n\n
\n\nTime Series\n- Forecasting\n- Seasonal Analysis\n- Trend Detection\n- Multivariate Models\n- Causal Analysis\n\n	\n\nBusiness Analytics\n- Customer Analytics\n- Market Analysis\n- Pricing Models\n- Predictive Analytics\n- Experimental Design\n\n

\n\n### Seamless Workflow\n\n```mermaid\ngraph LR\n A[Ask in Claude/Cursor] --> B[MCP Analytics]\n B --> C[Secure Processing]\n C --> D[Interactive Report]\n D --> E[Share Results]\n```\n\n\n## Example Usage\n\n### Basic Regression\n```\nUser: \"I have a CSV with house prices. Can you predict price based on size and location?\"\nClaude: [Runs linear regression, provides R², coefficients, and diagnostic plots]\n```\n\n### Customer Segmentation\n```\nUser: \"Segment my customers in sales_data.csv into meaningful groups\"\nClaude: [Performs k-means clustering, creates segment profiles with visualizations]\n```\n\n### Time Series Forecasting\n```\nUser: \"Forecast next quarter's revenue using our historical data\"\nClaude: [Applies ARIMA, generates predictions with confidence intervals]\n```\n\n## Security & Compliance\n\n### Enterprise Security Features\n\n- **Authentication**: OAuth2 via Auth0 with PKCE\n- **Encryption**: TLS 1.3 for all data transfers\n- **Processing**: Isolated Docker containers per analysis\n- **Data Handling**: Ephemeral processing, no persistence\n- **Access Control**: OAuth 2.0 scoped permissions with usage limits\n- **Audit Trail**: Complete logging for compliance\n\n### Privacy & Data Handling\n\n- **Data Privacy**: Ephemeral processing, no data retention\n- **User Rights**: Data deletion upon request\n- **Secure Processing**: Isolated containers per analysis\n- **Enterprise Options**: Contact us for compliance requirements\n\n[**Read full security documentation →**](https://github.com/embeddedlayers/mcp-analytics/blob/main/SECURITY.md)\n\n## Architecture\n\n```mermaid\nflowchart TB\n subgraph \"Client Integration\"\n CLI[CLI/SDK]\n Claude[Claude Desktop]\n Cursor[Cursor IDE]\n MCP[MCP Protocol]\n end\n\n subgraph \"API Gateway\"\n LB[Load Balancer]\n Auth[OAuth 2.0/Auth0]\n Rate[Rate Limiting]\n end\n\n subgraph \"Processing Layer\"\n Router[Request Router]\n Queue[Job Queue]\n Workers[Processing Workers]\n Docker[Docker Containers]\n end\n\n subgraph \"Analytics Engine\"\n Stats[Statistical Methods]\n ML[Machine Learning]\n TS[Time Series]\n Report[Report Generation]\n end\n\n subgraph \"Data Layer\"\n Cache[Results Cache]\n Storage[Secure Storage]\n Encrypt[Encryption Layer]\n end\n\n CLI --> LB\n Claude --> LB\n Cursor --> LB\n MCP --> LB\n\n LB --> Auth\n Auth --> Rate\n Rate --> Router\n\n Router --> Queue\n Queue --> Workers\n Workers --> Docker\n\n Docker --> Stats\n Docker --> ML\n Docker --> TS\n\n Stats --> Report\n ML --> Report\n TS --> Report\n\n Report --> Cache\n Cache --> Storage\n Storage --> Encrypt\n\n style Auth fill:#e8f5e9\n style Docker fill:#fff3e0\n style Report fill:#e3f2fd\n```\n\n## Performance\n\n- **Dataset Size**: Handles large datasets\n- **Processing Time**: Fast cloud-based processing\n- **Secure Infrastructure**: Isolated Docker containers\n- **API Access**: RESTful API with authentication\n\n## Getting Started\n\n[**Visit our website for pricing and signup →**](https://mcpanalytics.ai)\n\n## Documentation\n\n- [**Quick Start Guide**](https://github.com/embeddedlayers/mcp-analytics/blob/main/docs/quickstart.md) - Get running in under a minute\n- [**Architecture**](https://github.com/embeddedlayers/mcp-analytics/blob/main/docs/ARCHITECTURE.md) - How the platform works\n- [**Connectors**](https://github.com/embeddedlayers/mcp-analytics/blob/main/docs/connectors.md) - GA4, GSC, and CSV data sources\n- [**Pricing**](https://github.com/embeddedlayers/mcp-analytics/blob/main/docs/pricing.md) - Credits, tiers, and plans\n- [**How Credits Work**](https://mcpanalytics.ai/how-credits-work) - The credit model explained\n- [**Security**](https://github.com/embeddedlayers/mcp-analytics/blob/main/SECURITY.md) - Security & compliance details\n- [**Tutorials**](https://mcpanalytics.ai/tutorials) - Step-by-step guides\n\n## Support\n\n- **Issues**: [GitHub Issues](https://github.com/embeddedlayers/mcp-analytics/issues)\n- **Email**: support@mcpanalytics.ai\n- **Docs**: [mcpanalytics.ai/docs](https://mcpanalytics.ai/docs)\n- **Enterprise**: sales@mcpanalytics.ai\n\n## Comparison with Other MCP Servers\n\n| Feature | MCP Analytics | Google Analytics MCP | PostgreSQL MCP | Filesystem MCP |\n|---------|--------------|---------------------|----------------|----------------|\n| **Use Case** | Statistical Analysis | Web Metrics | Database Queries | File Access |\n| **Setup Time** | 30 seconds | OAuth + Config | Connection string | Path config |\n| **Data Sources** | Any CSV/JSON/URL | GA4 Only | PostgreSQL Only | Local files |\n| **Analysis Tools** | Full Suite | GA4 Metrics | SQL Only | Read/Write |\n| **Machine Learning** | ✅ Full Suite | ❌ | ❌ | ❌ |\n| **Visualizations** | ✅ Interactive | ✅ Dashboards | ❌ | ❌ |\n| **Shareable Reports** | ✅ | ❌ | ❌ | ❌ |\n\n[**Detailed comparison →**](https://mcpanalytics.ai/compare)\n\n## About MCP Analytics\n\nMCP Analytics is built by data scientists and engineers passionate about making advanced statistical analysis accessible through AI assistants. The platform runs validated, deterministic analysis modules — the same data and tool produce the same result every time, unlike LLM code generation.\n\n## Testing & Support\n\n### Testing Your Connection\n\nAfter installation, restart your MCP client and look for \"MCP Analytics\" in the available tools. You should see tools like `create_analysis`, `discover_tools`, `datasets_upload`, etc.\n\n```bash\n# Test the stdio proxy directly:\nMCP_ANALYTICS_API_KEY=mcp_your_key npx -y @mcp-analytics/mcp-analytics\n# Should output a \"[mcp-analytics] Connected to https://api.mcpanalytics.ai\" line with the tool count\n```\n\n### Troubleshooting\n\nIf MCP Analytics doesn't appear after installation:\n1. Ensure your config file is valid JSON\n2. Restart your MCP client completely\n3. Verify your API key starts with `mcp_`\n4. Check the client's developer console for errors\n5. Try running the npx command in a terminal to see errors\n\nFor support: support@mcpanalytics.ai\n\n## Contributing\n\nWhile the core server is proprietary, we welcome contributions to:\n\n- Documentation improvements\n- Example notebooks and use cases\n- Bug reports and feature requests\n- Community tools and integrations\n\nSee [CONTRIBUTING.md](https://github.com/embeddedlayers/mcp-analytics/blob/main/CONTRIBUTING.md) for guidelines.\n\n## License\n\nCopyright © 2026 PeopleDrivenAI LLC. All Rights Reserved.\n\nMCP Analytics is a product of PeopleDrivenAI LLC.\n\nThis is commercial software. Use of the MCP Analytics service is subject to our:\n- [Terms of Service](https://mcpanalytics.ai/terms)\n- [Privacy Policy](https://mcpanalytics.ai/privacy)\n\n---\n\n

\n\n**Ready to transform your data analysis workflow?**\n\n[**Get Started Free**](https://mcpanalytics.ai/signup) | [**Read Docs**](https://mcpanalytics.ai/docs) | [**View Demo**](https://mcpanalytics.ai/demo)\n\nBuilt by [MCP Analytics](https://mcpanalytics.ai) | Powered by R & Python\n\n

\n\n---\n\nIf MCP Analytics saves you time, a ⭐ on GitHub helps others find it.\n\n**Tags**: `mcp` `mcp-server` `model-context-protocol` `analytics` `data-analytics` `shopify-analytics` `stripe-analytics` `csv-analysis` `statistics` `machine-learning` `time-series` `clustering` `regression` `business-intelligence` `claude` `cursor` `ai-tools` `no-code-analytics` `forecasting` `customer-analytics`\n","changelogMarkdown","videoKey","requiredSecretsJson","publishedAt","priceCents","trialDays",0,"upstream",{"_114":115,"_116":117,"_118":119,"_120":121,"_122":123,"_124":125},"requiredSecrets",[],"tags",[99,100,101,102,103,104,105,106,107,108,109,110,111,112,113],"assets",[],"stats",{"_97":86,"_98":86},"ratingAvg","reviewCount","ai-agents","ai-tools","analytics","anthropic","business-intelligence","claude","csv-analysis","cursor","data-analytics","data-science","interactive-reports","llm-tools","machine-learning","no-code","shopify-analytics","topics",[99,100,101,102,103,104,105,106,107,108,109,110,111,126,127,128,112,113,129,130],"license","MIT","language","JavaScript","registryName","ai.mcpanalytics/analytics","homepage","https://mcpanalytics.ai","packages",[],"mcp","mcp-server","model-context-protocol","statistics","stripe-analytics","ENV",{"_133":134,"_135":136,"_137":138},"ENVIRONMENT","production","TURNSTILE_SITE_KEY","0x4AAAAAAB8-rEI2gNDf_QhU","SENTRY_DSN","https://45fd1229f78089d5c3ee78be128030e1@o4510583261757440.ingest.de.sentry.io/4510584253448272"]

\n\nStatistical Methods\n- Regression Analysis\n- Advanced Modeling\n- Hypothesis Testing\n- Survival Analysis\n- Bayesian Methods\n\n	\n\nMachine Learning\n- Ensemble Methods\n- Boosting Algorithms\n- Neural Networks\n- Clustering\n- Dimensionality Reduction\n\n
\n\nTime Series\n- Forecasting\n- Seasonal Analysis\n- Trend Detection\n- Multivariate Models\n- Causal Analysis\n\n	\n\nBusiness Analytics\n- Customer Analytics\n- Market Analysis\n- Pricing Models\n- Predictive Analytics\n- Experimental Design\n\n