Summary
Connects your data sources (CSV uploads, GA4, GSC, Shopify, Stripe) to a team of specialist agents that build custom analysis modules on demand. You ask a question, upload data or link a live source, and get back an interactive HTML report with charts, AI insights, and embedded R source code. The module joins your private library and reruns on fresh data for a fraction of the build cost. Exposes MCP tools for semantic discovery, dataset upload, tool execution, and report viewing. Currently in beta with a v2 rebuild underway. Reach for this when you need reproducible statistical analysis that compounds over time rather than one-off spreadsheet work.
Keeps your Mac awake while Claude Code, Codex or Cursor works. Lets it sleep when they are done.
Try free for 7 days →
Block distracting apps from your iPhone permanently without a 3rd party app. Free and open source.
Block now (100% free) →
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Free an open-source skills that make AI coding agents easier to understand, verify, and control.
Download for free →
Connect your Claude agent to live crypto prices and trading routes via 1inch
Get the MCP →Tools
Public tool metadata for what this MCP can expose to an agent.
19 tools
aboutGet platform info, pricing, usage stats, or documentation.1 params
Get platform info, pricing, usage stats, or documentation.
Parameters* required
topicstringTopic: platform, pricing, current_usage, manual, or a docs section
discover_toolsFind analysis tools matching your data or question. Semantic search across 50+ statistical and ML tools.2 params
Find analysis tools matching your data or question. Semantic search across 50+ statistical and ML tools.
Parameters* required
datasetstringDataset UUID to match tools against
querystringText query describing what you want to analyze
tools_schemaGet JSON schema for a tool — column_mapping and module_parameters required before tools_run.1 params
Get JSON schema for a tool — column_mapping and module_parameters required before tools_run.
Parameters* required
tool_namestringName of the tool
tools_runExecute an analysis tool. Returns a shareable interactive HTML report URL.2 params
Execute an analysis tool. Returns a shareable interactive HTML report URL.
Parameters* required
taskListobjectContains inputs: dataset, userContext, column_mapping, module_parameters
tool_namestringName of the tool to execute
tools_infoGet detailed information about a specific analysis tool — use cases, assumptions, data requirements.1 params
Get detailed information about a specific analysis tool — use cases, assumptions, data requirements.
Parameters* required
tool_namestringName of the tool
datasets_uploadGenerate a secure upload token for CSV files. Returns UUID + curl command for the user.1 params
Generate a secure upload token for CSV files. Returns UUID + curl command for the user.
Parameters* required
expires_inintegerToken expiration in secondsdefault: 300
datasets_listList and search uploaded datasets with fuzzy matching.2 params
List and search uploaded datasets with fuzzy matching.
Parameters* required
limitintegerMax resultsdefault: 20
searchstringSearch by name, description, or tags
datasets_readRead, filter, and search dataset rows. Use 'search' to find text across all columns, 'filters' for multi-column AND filtering, or filter_column for simple lookups. For row-level questions ('find rows where X'), use this — not an analysis tool.12 params
Read, filter, and search dataset rows. Use 'search' to find text across all columns, 'filters' for multi-column AND filtering, or filter_column for simple lookups. For row-level questions ('find rows where X'), use this — not an analysis tool.
Parameters* required
columnsarrayColumns to return
filter_columnstringfilter_operatorstringdefault: eq
filter_valuevaluefiltersarrayMulti-filter [{column, operator, value}]. Operators: eq, ne, gt, lt, contains, not_contains, regex, starts_with, ends_with, is_null, not_null
modestringfull, metadata, head, tail, sample
sample_sizeintegerdefault: 10
searchstringSearch text across ALL columns (case-insensitive)
secretstringDataset secret key
sort_bystringsort_orderstringdefault: asc
uuidstringDataset UUID
datasets_downloadGenerate a single-use download token for securely downloading datasets.1 params
Generate a single-use download token for securely downloading datasets.
Parameters* required
uuidstringDataset UUID
datasets_updateUpdate dataset metadata — name, description, tags, visibility.1 params
Update dataset metadata — name, description, tags, visibility.
Parameters* required
uuidstringDataset UUID
connectors_listList available data connectors — GA4, Google Search Console, and more.
List available data connectors — GA4, Google Search Console, and more.
No parameter schema in public metadata yet.
connectors_queryPull live data from a connected source using connector:// URIs.1 params
Pull live data from a connected source using connector:// URIs.
Parameters* required
uristringConnector URI (e.g., connector://mcpanalytics_gsc/search_analytics?...)
reports_listList analysis reports with metadata.1 params
List analysis reports with metadata.
Parameters* required
limitintegerMax resultsdefault: 10
reports_searchSearch reports by job ID, tool name, or keyword.2 params
Search reports by job ID, tool name, or keyword.
Parameters* required
job_idsarrayFilter by processing IDs
querystringSearch query
reports_viewView a specific report by processing ID.1 params
View a specific report by processing ID.
Parameters* required
processing_idstringProcessing ID from tools_run
report_cardsGet individual card data from a report for rendering.1 params
Get individual card data from a report for rendering.
Parameters* required
processing_idstringagent_advisorConversational AI that guides analysis and interprets results.1 params
Conversational AI that guides analysis and interprets results.
Parameters* required
messagestringYour question or request
billingCheck credit balance, subscription status, or open billing portal.1 params
Check credit balance, subscription status, or open billing portal.
Parameters* required
actionstringBilling actionone of
status · portal · usagedefault: statusmodule_requestRequest a custom analysis module to be built for your use case.1 params
Request a custom analysis module to be built for your use case.
Parameters* required
descriptionstringDescribe the analysis you need
MCP Analytics
A statistical analyst in your AI chat. Bring a dataset and a question, get back a citable, re-runnable report with its method named.
MCP Analytics is a Model Context Protocol server that answers business and statistical questions about your data, as deep as each question needs:
- Answer: a quick question about the data, read from all of it, shown with how we got it, and saved.
- Analytics: a tested statistical method runs on the data, and we interpret it with charts and a written report.
- Custom Analytics: a question only your business asks, built for your data from proven models, yours to re-run on next month's file.
Intelligent routing picks the depth: you describe the question, and the server says which path answers it and why. Analytics is repeatable: same data, same numbers. Every report names its method and the code that ran it, and runs again on new data.
It is for business and statistical questions about data, not a general-purpose assistant.
Website: mcpanalytics.ai · Free tools you can try in the browser: mcpanalytics.ai/free
Connect
Endpoint: https://api.mcpanalytics.ai/mcp/api-key (Streamable HTTP, JSON-RPC)
Authentication: an API key in the X-API-Key header. Create an account at mcpanalytics.ai and copy your key from your account settings.
{
"mcpServers": {
"mcpanalytics": {
"url": "https://api.mcpanalytics.ai/mcp/api-key",
"headers": { "X-API-Key": "mcp_your_key_here" }
}
}
}
Claude Code:
claude mcp add --transport http mcpanalytics https://api.mcpanalytics.ai/mcp/api-key --header "X-API-Key: mcp_your_key_here"
Browse before you sign up. Without a key the server answers in discovery mode: you can connect and list the tools, but not run anything.
curl -X POST https://api.mcpanalytics.ai/mcp/api-key \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
Start
Ask your AI assistant a question about your data, for example:
- "Upload sales.csv. What changed in revenue from May to June, and which channel drove it?"
- "Which customers are most likely to churn?"
- "Forecast next quarter's sales from this file."
The first call is the resolver: it reads your question and your data, executes nothing and charges nothing, and names the path that answers it (an answer, a library analysis, or a custom build) with the reason. Then it runs that path.
What you get
- A report with charts, tables and a written interpretation, with its method named and the code that ran it.
- Re-runs on new data: run the same analysis on next month's file.
- A library of your reports you can search and ask questions across.
Data and privacy
Your uploaded data is used only to answer your questions. See the privacy policy for what we keep and for how long. Security issues: see SECURITY.md.
Support
- Website: mcpanalytics.ai
- Email: support@mcpanalytics.ai
License
See LICENSE.
Featured
Keeps your Mac awake while Claude Code, Codex or Cursor works. Lets it sleep when they are done.
Try free for 7 days →Block distracting apps from your iPhone permanently without a 3rd party app. Free and open source.
Block now (100% free) →Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Free an open-source skills that make AI coding agents easier to understand, verify, and control.
Download for free →Connect your Claude agent to live crypto prices and trading routes via 1inch
Get the MCP →Registryactive
TransportHTTP
UpdatedMar 27, 2026
