@mseep/csv-editor 1.0.0

package/docs/docs/api/overview.md

@@ -0,0 +1,183 @@
+---
+sidebar_position: 1
+title: API Overview
+---
+
+# API Reference Overview
+
+CSV Editor provides a comprehensive set of tools for CSV manipulation through the Model Context Protocol (MCP). This reference documents all available tools, their parameters, and usage examples.
+
+## Tool Categories
+
+### 📁 I/O Operations
+Tools for loading and exporting CSV data in various formats.
+
+- [load_csv](./io/load-csv) - Load CSV from file
+- [load_csv_from_url](./io/load-url) - Load CSV from URL
+- [load_csv_from_content](./io/load-content) - Load CSV from string
+- [export_csv](./io/export) - Export to various formats
+- [get_session_info](./io/session-info) - Get session details
+- [list_sessions](./io/list-sessions) - List active sessions
+- [close_session](./io/close-session) - Close a session
+
+### 🔧 Data Manipulation
+Tools for transforming and modifying CSV data.
+
+- [filter_rows](./manipulation/filter) - Filter with conditions
+- [sort_data](./manipulation/sort) - Sort by columns
+- [select_columns](./manipulation/select) - Select specific columns
+- [rename_columns](./manipulation/rename) - Rename columns
+- [add_column](./manipulation/add-column) - Add new columns
+- [remove_columns](./manipulation/remove) - Remove columns
+- [update_column](./manipulation/update) - Update column values
+- [change_column_type](./manipulation/change-type) - Convert data types
+- [fill_missing_values](./manipulation/fill-missing) - Handle nulls
+- [remove_duplicates](./manipulation/remove-duplicates) - Deduplicate
+
+### 📊 Analysis
+Tools for statistical analysis and data exploration.
+
+- [get_statistics](./analysis/statistics) - Statistical summary
+- [get_column_statistics](./analysis/column-stats) - Column statistics
+- [get_correlation_matrix](./analysis/correlation) - Correlation analysis
+- [group_by_aggregate](./analysis/group-by) - Group operations
+- [get_value_counts](./analysis/value-counts) - Frequency counts
+- [detect_outliers](./analysis/outliers) - Find outliers
+- [profile_data](./analysis/profile) - Data profiling
+
+### ✅ Validation
+Tools for data quality and validation.
+
+- [validate_schema](./validation/schema) - Schema validation
+- [check_data_quality](./validation/quality) - Quality metrics
+- [find_anomalies](./validation/anomalies) - Anomaly detection
+
+### 💾 Auto-Save & History
+Tools for persistence and version control.
+
+- [configure_auto_save](./persistence/auto-save) - Configure auto-save
+- [get_auto_save_status](./persistence/auto-save-status) - Check status
+- [trigger_manual_save](./persistence/manual-save) - Manual save
+- [undo](./persistence/undo) - Undo last operation
+- [redo](./persistence/redo) - Redo operation
+- [get_history](./persistence/history) - View history
+- [restore_to_operation](./persistence/restore) - Time travel
+
+## Common Patterns
+
+### Session Management
+
+All operations require a session ID obtained from loading data:
+
+```python
+# Load data and get session ID
+result = await load_csv(file_path="/path/to/data.csv")
+session_id = result["session_id"]
+
+# Use session ID in subsequent operations
+await filter_rows(session_id=session_id, conditions=[...])
+await export_csv(session_id=session_id, format="excel")
+```
+
+### Error Handling
+
+All tools return consistent error responses:
+
+```json
+{
+  "success": false,
+  "error": "Error message",
+  "error_type": "ValueError",
+  "details": "Additional context"
+}
+```
+
+### Response Format
+
+Successful operations return:
+
+```json
+{
+  "success": true,
+  "data": {...},
+  "message": "Operation completed",
+  "metadata": {
+    "rows_affected": 100,
+    "execution_time": 0.123
+  }
+}
+```
+
+## Data Types
+
+### Supported Column Types
+- `string` - Text data
+- `integer` - Whole numbers
+- `float` - Decimal numbers
+- `datetime` - Date and time
+- `boolean` - True/False values
+- `category` - Categorical data
+
+### Export Formats
+- `csv` - Comma-separated values
+- `tsv` - Tab-separated values
+- `json` - JSON array or records
+- `excel` - Excel spreadsheet (.xlsx)
+- `parquet` - Apache Parquet format
+- `html` - HTML table
+- `markdown` - Markdown table
+
+## Filter Operators
+
+| Operator | Description | Example |
+|----------|-------------|---------|
+| `==` | Equal to | `{"column": "status", "operator": "==", "value": "active"}` |
+| `!=` | Not equal to | `{"column": "status", "operator": "!=", "value": "inactive"}` |
+| `>` | Greater than | `{"column": "amount", "operator": ">", "value": 1000}` |
+| `<` | Less than | `{"column": "age", "operator": "<", "value": 18}` |
+| `>=` | Greater than or equal | `{"column": "score", "operator": ">=", "value": 80}` |
+| `<=` | Less than or equal | `{"column": "price", "operator": "<=", "value": 100}` |
+| `contains` | Contains substring | `{"column": "name", "operator": "contains", "value": "John"}` |
+| `starts_with` | Starts with | `{"column": "email", "operator": "starts_with", "value": "admin"}` |
+| `ends_with` | Ends with | `{"column": "file", "operator": "ends_with", "value": ".csv"}` |
+| `in` | In list | `{"column": "category", "operator": "in", "value": ["A", "B"]}` |
+| `not_in` | Not in list | `{"column": "status", "operator": "not_in", "value": ["deleted"]}` |
+| `is_null` | Is null | `{"column": "email", "operator": "is_null"}` |
+| `not_null` | Is not null | `{"column": "phone", "operator": "not_null"}` |
+
+## Aggregation Functions
+
+Available aggregation functions for `group_by_aggregate`:
+
+- `sum` - Sum of values
+- `mean` - Average value
+- `median` - Median value
+- `min` - Minimum value
+- `max` - Maximum value
+- `count` - Count of non-null values
+- `std` - Standard deviation
+- `var` - Variance
+- `first` - First value
+- `last` - Last value
+
+## Best Practices
+
+1. **Always close sessions** when done to free resources
+2. **Use chunking** for large files (>100MB)
+3. **Enable auto-save** for important data
+4. **Validate data** before processing
+5. **Use appropriate data types** for better performance
+6. **Handle errors gracefully** in your client code
+
+## Rate Limits
+
+- Maximum file size: 1GB (configurable)
+- Maximum concurrent sessions: 10 per user
+- Session timeout: 1 hour (configurable)
+- Maximum rows per operation: 10 million
+
+## Next Steps
+
+- Explore specific tool documentation in each category
+- See [Examples](../examples) for real-world use cases
+- Check [Tutorials](../tutorials/quickstart) for step-by-step guides

package/docs/docs/installation.md

@@ -0,0 +1,252 @@
+---
+sidebar_position: 2
+title: Installation
+---
+
+# Installation Guide
+
+Get CSV Editor up and running in just 2 minutes! This guide covers all installation methods and client configurations.
+
+## Prerequisites
+
+- **Python 3.8+** (3.11+ recommended for best performance)
+- **Operating System**: Windows, macOS, or Linux
+- **Package Manager**: uv (recommended), pip, or conda
+
+## Quick Install (Recommended)
+
+### Using uv (Fastest)
+
+[uv](https://github.com/astral-sh/uv) is an ultra-fast Python package manager that makes installation simple:
+
+```bash
+# Install uv (one-time setup)
+curl -LsSf https://astral.sh/uv/install.sh | sh
+# Or on Windows: powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
+
+# Clone and install CSV Editor
+git clone https://github.com/santoshray02/csv-editor.git
+cd csv-editor
+uv sync
+
+# Run the server
+uv run csv-editor
+```
+
+### Using pip
+
+```bash
+# Clone the repository
+git clone https://github.com/santoshray02/csv-editor.git
+cd csv-editor
+
+# Create virtual environment
+python -m venv .venv
+source .venv/bin/activate  # On Windows: .venv\Scripts\activate
+
+# Install dependencies
+pip install -e .
+
+# Run the server
+python -m csv_editor.server
+```
+
+## Client Configuration
+
+### Claude Desktop
+
+Configure Claude Desktop to use CSV Editor as an MCP server.
+
+#### macOS
+Edit `~/Library/Application Support/Claude/claude_desktop_config.json`:
+
+```json
+{
+  "mcpServers": {
+    "csv-editor": {
+      "command": "uv",
+      "args": ["tool", "run", "csv-editor"],
+      "cwd": "/path/to/csv-editor",
+      "env": {
+        "CSV_MAX_FILE_SIZE": "1073741824",
+        "CSV_SESSION_TIMEOUT": "3600"
+      }
+    }
+  }
+}
+```
+
+#### Windows
+Edit `%APPDATA%\Claude\claude_desktop_config.json`:
+
+```json
+{
+  "mcpServers": {
+    "csv-editor": {
+      "command": "uv",
+      "args": ["tool", "run", "csv-editor"],
+      "cwd": "C:\\path\\to\\csv-editor",
+      "env": {
+        "CSV_MAX_FILE_SIZE": "1073741824",
+        "CSV_SESSION_TIMEOUT": "3600"
+      }
+    }
+  }
+}
+```
+
+#### Linux
+Edit `~/.config/Claude/claude_desktop_config.json`:
+
+```json
+{
+  "mcpServers": {
+    "csv-editor": {
+      "command": "uv",
+      "args": ["tool", "run", "csv-editor"],
+      "cwd": "/home/user/csv-editor",
+      "env": {
+        "CSV_MAX_FILE_SIZE": "1073741824",
+        "CSV_SESSION_TIMEOUT": "3600"
+      }
+    }
+  }
+}
+```
+
+### VS Code Extensions
+
+#### Continue
+Edit `~/.continue/config.json`:
+
+```json
+{
+  "mcpServers": {
+    "csv-editor": {
+      "command": "uv",
+      "args": ["tool", "run", "csv-editor"],
+      "cwd": "/path/to/csv-editor"
+    }
+  }
+}
+```
+
+#### Cline
+Add to VS Code settings (`settings.json`):
+
+```json
+{
+  "cline.mcpServers": {
+    "csv-editor": {
+      "command": "uv",
+      "args": ["tool", "run", "csv-editor"],
+      "cwd": "/path/to/csv-editor"
+    }
+  }
+}
+```
+
+### Other Clients
+
+For detailed configuration of other clients (Windsurf, Zed, etc.), see [MCP_CONFIG.md](https://github.com/santoshray02/csv-editor/blob/main/MCP_CONFIG.md).
+
+## Advanced Installation
+
+### Install with All Features
+
+```bash
+# With uv
+uv sync --all-extras
+
+# With pip
+pip install -e ".[all]"
+```
+
+### Install for Development
+
+```bash
+# With uv
+uv sync --all-extras
+uv run pre-commit install
+
+# With pip
+pip install -e ".[dev]"
+pre-commit install
+```
+
+### Global Installation with pipx
+
+```bash
+pipx install git+https://github.com/santoshray02/csv-editor.git
+```
+
+## Environment Variables
+
+Configure CSV Editor behavior with these environment variables:
+
+| Variable | Default | Description |
+|----------|---------|-------------|
+| `CSV_MAX_FILE_SIZE` | 1GB | Maximum file size in bytes |
+| `CSV_SESSION_TIMEOUT` | 3600 | Session timeout in seconds |
+| `CSV_CHUNK_SIZE` | 10000 | Rows per processing chunk |
+| `CSV_AUTO_SAVE` | true | Enable auto-save by default |
+| `CSV_LOG_LEVEL` | INFO | Logging level |
+
+## Verification
+
+### Test the Installation
+
+```bash
+# Check if server starts
+uv run csv-editor --help
+
+# Run with verbose output
+CSV_LOG_LEVEL=DEBUG uv run csv-editor
+```
+
+### Test with MCP Inspector
+
+```bash
+# Install MCP Inspector
+npm install -g @modelcontextprotocol/inspector
+
+# Test the server
+mcp-inspector uv tool run csv-editor
+```
+
+### Verify in Your Client
+
+1. **Claude Desktop**: Look for "csv-editor" in the MCP servers list
+2. **VS Code**: Check the extension's MCP panel
+3. **Command Line**: Run a test command
+
+## Troubleshooting
+
+### Common Issues
+
+#### Server not starting
+- Check Python version: `python --version` (must be 3.8+)
+- Verify installation: `uv run csv-editor --version`
+- Check logs: `CSV_LOG_LEVEL=DEBUG uv run csv-editor`
+
+#### Client can't connect
+- Verify the path in your configuration is correct
+- Ensure the server is running
+- Check firewall settings for local connections
+
+#### Permission errors
+- On macOS/Linux: Check file permissions
+- On Windows: Run as administrator if needed
+
+### Getting Help
+
+- [GitHub Issues](https://github.com/santoshray02/csv-editor/issues)
+- [GitHub Discussions](https://github.com/santoshray02/csv-editor/discussions)
+- [Documentation](https://csv-editor-docs.vercel.app)
+
+## Next Steps
+
+Now that CSV Editor is installed, continue to:
+- [Quick Start Tutorial](./tutorials/quickstart) - Learn the basics
+- [API Reference](./api/overview) - Explore all available tools
+- [Examples](./examples) - See real-world use cases

package/docs/docs/intro.md

@@ -0,0 +1,87 @@
+---
+sidebar_position: 1
+title: Introduction
+slug: /intro
+---
+
+# Welcome to CSV Editor
+
+**Transform how AI assistants work with CSV data.** CSV Editor is a high-performance MCP (Model Context Protocol) server that gives Claude, ChatGPT, and other AI assistants powerful data manipulation capabilities through simple commands.
+
+## What is CSV Editor?
+
+CSV Editor is a comprehensive data processing tool that bridges the gap between AI assistants and complex data operations. It provides 40+ specialized tools for CSV operations, turning AI assistants into powerful data analysts.
+
+## Key Features
+
+### 🚀 Core Capabilities
+- **Session Management**: Multi-user support with isolated sessions
+- **Auto-Save**: Automatic data persistence with multiple strategies
+- **History & Undo/Redo**: Complete operation history with time-travel
+- **Multiple Data Sources**: Load from files, URLs, or strings
+- **Export Formats**: CSV, JSON, Excel, Parquet, HTML, Markdown
+
+### 📊 Data Operations
+- Complex filtering with AND/OR logic
+- Multi-column sorting
+- Column operations (add, remove, rename, update)
+- Smart type conversion
+- Missing value handling
+- Duplicate removal
+
+### 📈 Analytics
+- Statistical analysis with percentiles
+- Correlation matrices (Pearson, Spearman, Kendall)
+- Group-by aggregations
+- Outlier detection (IQR, Z-score)
+- Comprehensive data profiling
+
+### ✅ Validation
+- Schema validation
+- Data quality scoring
+- Anomaly detection
+- Pattern matching
+
+## Why Choose CSV Editor?
+
+| Feature | CSV Editor | Traditional Tools |
+|---------|-----------|------------------|
+| **AI Integration** | Native MCP protocol | Manual operations |
+| **Auto-Save** | Automatic with strategies | Manual save required |
+| **History Tracking** | Full undo/redo | Limited or none |
+| **Session Management** | Multi-user isolated | Single user |
+| **Performance** | Handles GB+ files | Memory limitations |
+
+## Quick Example
+
+Here's what your AI assistant can do with CSV Editor:
+
+```python
+# Natural language commands become data operations
+"Load the sales data and remove duplicates"
+"Filter for Q4 2024 transactions over $10,000"  
+"Calculate correlation between price and quantity"
+"Fill missing values with the median"
+"Export as Excel with the analysis"
+```
+
+## Getting Started
+
+Ready to supercharge your AI's data capabilities? Continue to the [Installation Guide](./installation) to set up CSV Editor in just 2 minutes!
+
+## Learn More
+
+- [Installation Guide](./installation) - Set up CSV Editor
+- [Quick Start Tutorial](./tutorials/quickstart) - Your first data processing
+- [API Reference](./api/overview) - Complete tool documentation
+- [Examples](./examples) - Real-world use cases
+
+## Community & Support
+
+- [GitHub Repository](https://github.com/santoshray02/csv-editor)
+- [GitHub Discussions](https://github.com/santoshray02/csv-editor/discussions)
+- [Report Issues](https://github.com/santoshray02/csv-editor/issues)
+
+---
+
+**Built with ❤️ using [FastMCP](https://github.com/jlowin/fastmcp) and [Pandas](https://pandas.pydata.org/)**

package/docs/docs/tutorial-basics/_category_.json

@@ -0,0 +1,8 @@
+{
+  "label": "Tutorial - Basics",
+  "position": 2,
+  "link": {
+    "type": "generated-index",
+    "description": "5 minutes to learn the most important Docusaurus concepts."
+  }
+}

package/docs/docs/tutorial-basics/congratulations.md

@@ -0,0 +1,23 @@
+---
+sidebar_position: 6
+---
+
+# Congratulations!
+
+You have just learned the **basics of Docusaurus** and made some changes to the **initial template**.
+
+Docusaurus has **much more to offer**!
+
+Have **5 more minutes**? Take a look at **[versioning](../tutorial-extras/manage-docs-versions.md)** and **[i18n](../tutorial-extras/translate-your-site.md)**.
+
+Anything **unclear** or **buggy** in this tutorial? [Please report it!](https://github.com/facebook/docusaurus/discussions/4610)
+
+## What's next?
+
+- Read the [official documentation](https://docusaurus.io/)
+- Modify your site configuration with [`docusaurus.config.js`](https://docusaurus.io/docs/api/docusaurus-config)
+- Add navbar and footer items with [`themeConfig`](https://docusaurus.io/docs/api/themes/configuration)
+- Add a custom [Design and Layout](https://docusaurus.io/docs/styling-layout)
+- Add a [search bar](https://docusaurus.io/docs/search)
+- Find inspirations in the [Docusaurus showcase](https://docusaurus.io/showcase)
+- Get involved in the [Docusaurus Community](https://docusaurus.io/community/support)

package/docs/docs/tutorial-basics/create-a-blog-post.md

@@ -0,0 +1,34 @@
+---
+sidebar_position: 3
+---
+
+# Create a Blog Post
+
+Docusaurus creates a **page for each blog post**, but also a **blog index page**, a **tag system**, an **RSS** feed...
+
+## Create your first Post
+
+Create a file at `blog/2021-02-28-greetings.md`:
+
+```md title="blog/2021-02-28-greetings.md"
+---
+slug: greetings
+title: Greetings!
+authors:
+  - name: Joel Marcey
+    title: Co-creator of Docusaurus 1
+    url: https://github.com/JoelMarcey
+    image_url: https://github.com/JoelMarcey.png
+  - name: Sébastien Lorber
+    title: Docusaurus maintainer
+    url: https://sebastienlorber.com
+    image_url: https://github.com/slorber.png
+tags: [greetings]
+---
+
+Congratulations, you have made your first post!
+
+Feel free to play around and edit this post as much as you like.
+```
+
+A new blog post is now available at [http://localhost:3000/blog/greetings](http://localhost:3000/blog/greetings).

package/docs/docs/tutorial-basics/create-a-document.md

@@ -0,0 +1,57 @@
+---
+sidebar_position: 2
+---
+
+# Create a Document
+
+Documents are **groups of pages** connected through:
+
+- a **sidebar**
+- **previous/next navigation**
+- **versioning**
+
+## Create your first Doc
+
+Create a Markdown file at `docs/hello.md`:
+
+```md title="docs/hello.md"
+# Hello
+
+This is my **first Docusaurus document**!
+```
+
+A new document is now available at [http://localhost:3000/docs/hello](http://localhost:3000/docs/hello).
+
+## Configure the Sidebar
+
+Docusaurus automatically **creates a sidebar** from the `docs` folder.
+
+Add metadata to customize the sidebar label and position:
+
+```md title="docs/hello.md" {1-4}
+---
+sidebar_label: 'Hi!'
+sidebar_position: 3
+---
+
+# Hello
+
+This is my **first Docusaurus document**!
+```
+
+It is also possible to create your sidebar explicitly in `sidebars.js`:
+
+```js title="sidebars.js"
+export default {
+  tutorialSidebar: [
+    'intro',
+    // highlight-next-line
+    'hello',
+    {
+      type: 'category',
+      label: 'Tutorial',
+      items: ['tutorial-basics/create-a-document'],
+    },
+  ],
+};
+```

package/docs/docs/tutorial-basics/create-a-page.md

@@ -0,0 +1,43 @@
+---
+sidebar_position: 1
+---
+
+# Create a Page
+
+Add **Markdown or React** files to `src/pages` to create a **standalone page**:
+
+- `src/pages/index.js` → `localhost:3000/`
+- `src/pages/foo.md` → `localhost:3000/foo`
+- `src/pages/foo/bar.js` → `localhost:3000/foo/bar`
+
+## Create your first React Page
+
+Create a file at `src/pages/my-react-page.js`:
+
+```jsx title="src/pages/my-react-page.js"
+import React from 'react';
+import Layout from '@theme/Layout';
+
+export default function MyReactPage() {
+  return (
+    <Layout>
+      <h1>My React page</h1>
+      <p>This is a React page</p>
+    </Layout>
+  );
+}
+```
+
+A new page is now available at [http://localhost:3000/my-react-page](http://localhost:3000/my-react-page).
+
+## Create your first Markdown Page
+
+Create a file at `src/pages/my-markdown-page.md`:
+
+```mdx title="src/pages/my-markdown-page.md"
+# My Markdown page
+
+This is a Markdown page
+```
+
+A new page is now available at [http://localhost:3000/my-markdown-page](http://localhost:3000/my-markdown-page).