Skip to main content
Glama
Ratnaditya-J

CSVGlow

by Ratnaditya-J
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

csvglow

csvglow MCP server

Generate beautiful, interactive HTML dashboards from CSV/Excel files. One command, zero config.

csvglow sales.csv

Opens a self-contained HTML dashboard in your browser with auto-detected charts, smart multi-column insights, correlations, and a sortable data table. Dark gradient theme. Copy any chart to your clipboard.

Install

pip install csvglow

Or via npx (no install needed):

npx csvglow data.csv

Related MCP server: CSV MCP Server

Usage

csvglow data.csv                    # CSV to dashboard, opens in browser
csvglow report.xlsx                 # Excel works too
csvglow data.csv -o dashboard.html  # Custom output path
csvglow data.csv --no-open          # Don't auto-open browser

What it generates

  • Smart findings — multi-column narrative analysis that cross-references metrics to surface contradictions, efficiency gaps, and top/underperformers

  • Histograms for every numeric column with mean, median, std, quartiles, and outlier counts

  • Bar charts for categorical columns

  • Cross analysis — automatic categorical x numeric crosstabs with overall mean lines

  • Time series line charts with area fill for date columns

  • Correlation heatmap between numeric columns

  • Scatter plots for highly correlated pairs (|r| > 0.7)

  • Sortable, filterable data table (first 1000 rows)

  • Copy button on each chart for pasting into slides

Output is a single self-contained HTML file. No server, no CDN, works offline.

MCP Server

csvglow works as an MCP tool in any MCP-compatible client. Once configured, ask your AI assistant to generate a dashboard from a file path.

Pick your client and add csvglow to its MCP config file:

Client

Config file location

Cursor

.cursor/mcp.json in your project root

Windsurf

~/.windsurf/mcp.json

Add this to the config:

{
  "mcpServers": {
    "csvglow": {
      "command": "npx",
      "args": ["-y", "csvglow", "--mcp"]
    }
  }
}

Uses npx so there's nothing extra to install.

If you already have csvglow installed via pip, use "command": "csvglow" with "args": ["--mcp"] instead.

OpenClaw Skill

csvglow is available as an OpenClaw skill. Any OpenClaw-compatible client can discover and use it automatically — no manual config needed.

Supported formats

  • .csv / .tsv (auto-detected delimiter)

  • .xls

  • .xlsx (first sheet only — multi-sheet support coming soon)

Changelog

0.1.0

  • Initial release

  • Auto-detection of column types (numeric, categorical, datetime, identifier)

  • Smart findings: contradiction detection, efficiency analysis, top/underperformer identification across multiple columns

  • Histograms with stats sidebar, bar charts, cross-analysis crosstabs, time series, correlation heatmap, scatter plots

  • Sortable/filterable data table

  • Copy-to-clipboard for all charts

  • MCP server mode (csvglow --mcp)

  • OpenClaw skill support

  • Smart sampling for large files (100k+ rows)

Roadmap

  • Multi-sheet Excel support

  • Multi-file support with join keys

  • Light theme

  • Custom color palettes

  • PDF export

License

MIT

Available Tools

1 tool
generate_dashboardA

Generate a beautiful, interactive HTML dashboard from a CSV or Excel file.

Analyzes the data and produces charts, statistics, correlations, insights, and a sortable data table — all in a single self-contained HTML file.

Use this tool when the user wants to visualize, explore, analyze, or create a dashboard from a CSV, TSV, XLS, or XLSX file.

Args: file_path: Absolute path to a CSV, TSV, XLS, or XLSX file. output_path: Where to save the HTML dashboard. Defaults to .html. open_browser: Whether to auto-open the dashboard in the browser.

ParametersJSON Schema
NameRequiredDescriptionDefault
file_pathYes
output_pathNo
open_browserNo

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It states the tool analyzes data and produces a self-contained HTML file, implying it is a read-only operation. It discloses default behaviors for output_path and open_browser. However, it does not mention potential side effects (e.g., file overwriting) or resource limits, but the overall behavior is reasonably transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured: a lead sentence, a capabilities paragraph, a usage line, and an Args list. It is not overly verbose and every sentence adds value. The Args section is clear. Minor improvement could be to combine the first two sentences, but overall it is efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (3 params, no output schema, no siblings), the description covers the core functionality, parameter details, and usage context. It explains what the output is (HTML dashboard) and its features. The description is complete enough for an agent to select and invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate. The Args section adds key details: file_path must be an absolute path to CSV/TSV/XLS/XLSX, output_path defaults to <input>.html, open_browser defaults to true. This meaningfully augments the schema, though some details like expected file size limits are missing.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool generates a beautiful, interactive HTML dashboard from CSV/Excel files. It specifies the verb 'generate', the resource 'dashboard', and lists the capabilities (charts, statistics, correlations, sortable table). This is specific and distinguishes it clearly even without siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'Use this tool when the user wants to visualize, explore, analyze, or create a dashboard from a CSV, TSV, XLS, or XLSX file.' This provides clear context for when to use the tool. Since there are no siblings, absence of when-not-to-use or alternatives is acceptable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.5/5.0
Disambiguation5/5

Only one tool exists, so there is no possibility of confusion with other tools.

Naming Consistency5/5

With a single tool, naming is trivially consistent; the verb_noun pattern is clear.

Tool Count5/5

The single tool directly matches the server's purpose of generating dashboards from CSV/Excel files, which is appropriately scoped.

Completeness5/5

The tool generates a comprehensive HTML dashboard with charts, statistics, and insights, covering the full scope implied by the server name without obvious gaps.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • CSV Editor

    santoshray02
    A
    license
    B
    quality
    C
    maintenance
    Comprehensive CSV processing MCP server with 40+ operations for data manipulation, analysis, and validation. Features auto-save, undo/redo, and handles GB+ files
    4
    39
    24
    MIT

  • CSV MCP Server

    NovaAI-innovation
    F
    license
    A
    quality
    D
    maintenance
    Enables comprehensive CSV file management including creating, editing, analyzing, and transforming CSV data anywhere in the filesystem. Provides statistical analysis, data validation, filtering, and grouping capabilities through MCP protocol over stdio transport.
    15

  • csv-analyzer

    viajeraune
    F
    license
    Not graded
    quality
    D
    maintenance
    A local MCP server for analyzing CSV files from your filesystem, particularly suited for chatbot conversation logs. Allows listing, reading, filtering, merging, and statistical analysis of CSV data via natural language.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Ratnaditya-J/csvglow'

If you have feedback or need assistance with the MCP directory API, please join our Discord server