This MCP server locally analyzes CSV/XLSX tables and produces statistical reports, Chinese Markdown insights, and optional Excel workbooks with native charts.
Analyze .csv/.xlsx inputs supplied as base64 or a direct HTTPS URL; files over 30 MB are rejected.
Compute shape, duplicate rows, missing-rate diagnostics, numeric statistics, categorical top frequencies, and significant pairwise Pearson correlations (|r| >= 0.5).
Generate a Chinese Markdown insights report.
Optionally return a base64 .xlsx workbook with summary/statistics/detail/distribution sheets and native bar charts.
Check service status and free-tier limits with health().
Enforce an anonymous free quota (100 tables / 30 days per client) unless a paid api_key is supplied.
Run locally with no pandas, no required API key, and optional stdio or streamable-http transport.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@data-report-mcp analyze sales.csv and return an Excel report with charts"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
📄 Project landing page (use cases and install guide): https://diyaluo.github.io/data-report-mcp/
A local-first Model Context Protocol (MCP) server that turns a CSV/XLSX table into a real data analysis report — summary statistics, duplicate / missing diagnostics, top category frequencies, pairwise correlations, a Chinese Markdown insights writeup, and an Excel workbook with native interactive charts.
🔒 100% local, no API key, no network. Business / financial spreadsheets
never leave the machine. There is no telemetry upload — only an optional
local usage counter under ~/.cache/data-report-mcp.
🧮 No pandas. Runs on the standard library + openpyxl, so it bundles
small and starts fast inside an MCP host.
🔌 Two transports: stdio (Claude Desktop / Cursor / any MCP client) and streamable-http for a hosted endpoint.
🆓 Anonymous free tier (100 tables / 30 days per client); over-quota returns
an in-band QUOTA_EXCEEDED signal, it never silently bills.
Tool | Purpose |
| Analyze a |
| Service status + free-tier limits. |
analyze_table accepts the raw file as base64 (preferred) or a direct
https URL to a .csv/.xlsx. Inputs larger than 30 MB are rejected.
Related MCP server: MCP Tabular Data Analysis Server
pip install -e . # or: pip install data-report-mcp
# stdio (default MCP transport)
python -m data_report_mcp.server
# streamable-http
REMOTE_TRANSPORT=http MCP_PORT=5070 python -m data_report_mcp.server{
"mcpServers": {
"data-report": {
"command": "python",
"args": ["-m", "data_report_mcp.server"]
}
}
}Var | Default | Meaning |
|
| anonymous monthly table limit |
| (unset) | paid key that bypasses the quota |
|
| local usage-counter directory |
|
| http transport options |
Overall: row/column count, duplicate rows, columns with missing rate ≥ 20%.
Numeric columns: min / max / mean / median / sum / stdev / missing rate.
Categorical columns: unique count + top-5 value frequencies.
Significant pairwise correlations (Pearson |r| ≥ 0.5).
An Excel workbook (return_xlsx=true) with sheets 概览 / 数值统计 / 明细 /
分布_* (each with a native bar chart) / 显著相关.
Output is a starting point for analysis, not a conclusion: correlation is not causation — combine it with business judgment.
MIT. Core analysis adapted from the open data-report local toolkit.
Analyze a CSV/XLSX table fully locally: infer numeric/categorical columns, compute shape, missing rate, duplicates, min/max/mean/median/sum/ stddev, top frequencies for text columns and pairwise correlations (|r|>=0.5), and return a Chinese Markdown insights report. Optionally a base64 Excel workbook with native interactive bar charts.
Args: file_base64: raw CSV/XLSX content as base64 (preferred). file_url: direct HTTPS URL to a .csv/.xlsx (alternative). filename: original filename (used only to decide csv vs xlsx). charts: max category columns to chart in the xlsx workbook. return_xlsx: when true, include the generated workbook as base64. api_key: paid key to bypass the anonymous monthly quota.
Inputs: charts, api_key, file_url, filename, +2 more.
Service health + free-tier limits. No auth required.
Inputs: no named parameters.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 2 tools
health and analyze_table have completely distinct purposes: one checks service status and quota, the other performs local table analysis. There is no overlap or ambiguity in choosing between them.
Both names use snake_case consistently. However, 'health' is a bare noun while 'analyze_table' follows a verb_noun pattern, creating a minor structural inconsistency.
With only 2 tools, and one being a trivial health check, the functional surface is thin for a server named data-report-mcp. The single analyze_table tool is comprehensive, but the overall set feels under-scoped.
The core single-table analysis and reporting workflow is well covered, including stats, correlations, and optional charts. However, notable gaps exist: no support for multi-table comparison, time-series analysis, data cleaning, or saved report retrieval, limiting real-world reporting use cases.
Messy CSV, JSON, Excel, SPSS/Stata/SAS and PDF tables to typed Parquet; inspect, query, join.
Upload spreadsheets, get plain-English analysis with real computed charts and quality scores.
Convert and clean tables: CSV, JSON, dedupe, stats. Free.
A statistical analyst in your AI chat: bring data and a question, get a citable, re-runnable report.