Analytics MCP server
Commit Oct 26, 2026Generates citable, re-runnable statistical reports and data interpretations from datasets through an AI chat interface.
Also known as embeddedlayers/mcp-analytics, mcp-analytics
- Stars
- 9
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.0.8
- Last commit
- Oct 26, 2026
- License
- MIT
What is Analytics MCP?
Analytics generates citable, re-runnable statistical reports and data interpretations from datasets through an AI chat interface.
Summary generated from the project's README
About Analytics MCP server
MCP Analytics provides a specialized interface for generating statistical reports and data interpretations through an AI chat. It functions as a remote server via a streamable HTTP JSON-RPC endpoint, requiring an API key provided in the X-API-Key header for full functionality. Users can connect using standard MCP configurations or via Claude Code. While a discovery mode allows users to list tools without a key, executing analysis requires an account from the service website.
The server uses intelligent routing to determine the appropriate depth for a query, choosing between a quick answer, a standard analytics path with charts, or a custom analytics build. It is designed specifically for business and statistical inquiries rather than general assistance. Every output includes the specific method used and the code executed, ensuring that reports are citable and repeatable. This allows developers to run the same models on new datasets, such as monthly files, to maintain consistency in their reporting.
What you can do with it
- 1Perform revenue change analysisAsk the AI to identify specific drivers behind revenue fluctuations between two time periods in a CSV file.
- 2Predict customer behaviorRequest an analysis to identify which specific customers show signs of being likely to churn.
- 3Generate sales forecastsUse a dataset to project upcoming sales figures for the next quarter.
- 4Repeatable monthly reportingApply a previously built custom model to a new data file to get updated results.
Written from the project's README. Every use case is checked against a quote from it.
How to install Analytics MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Analytics MCP in Claude Code
$ claude mcp add --transport http mcp-analytics https://api.mcpanalytics.ai/mcp/api-keyInstall Analytics MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"mcp-analytics": {
"url": "https://api.mcpanalytics.ai/mcp/api-key"
}
}
}Install Analytics MCP in VS Code
.vscode/mcp.json
{
"servers": {
"mcp-analytics": {
"type": "http",
"url": "https://api.mcpanalytics.ai/mcp/api-key"
}
}
}Install Analytics MCP in VS Code CLI
$ code --add-mcp '{"name":"mcp-analytics","type":"http","url":"https://api.mcpanalytics.ai/mcp/api-key"}'Install Analytics MCP in Codex
$ codex mcp add mcp-analytics --url https://api.mcpanalytics.ai/mcp/api-keyInstall Analytics MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.mcp-analytics] url = "https://api.mcpanalytics.ai/mcp/api-key"
Install Analytics MCP in Gemini CLI
$ gemini mcp add -s user --transport http mcp-analytics https://api.mcpanalytics.ai/mcp/api-keyInstall Analytics MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"mcp-analytics": {
"url": "https://api.mcpanalytics.ai/mcp/api-key",
"type": "http"
}
}
}Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableembeddedlayers/mcp-analytics is public and reachablegithub.com/embeddedlayers/mcp-analytics ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-26github.com/embeddedlayers/mcp-analytics ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2024-11-05 in 314 msPass
README
View on GitHubMCP 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.
Analytics MCP questions
How do I add Analytics MCP to Claude Code?
Run claude mcp add --transport http mcp-analytics https://api.mcpanalytics.ai/mcp/api-key in your terminal. Add --scope user to make it available in every project.
How do I add Analytics MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Can I try the server before signing up?
Yes, you can connect in discovery mode without a key to list the available tools, though you cannot execute them.
What kind of output does the server provide?
The server provides reports containing charts, tables, written interpretations, the named statistical method used, and the code that executed the analysis.
Is my data kept private?
Uploaded data is used exclusively to answer your specific questions.