CSV Editor - AI-Powered CSV Processing via MCP

Transform how AI assistants work with CSV data. CSV Editor is a high-performance MCP server that gives Claude, ChatGPT, and other AI assistants powerful data manipulation capabilities through simple commands.

AI assistants struggle with complex data operations - they can read files but lack tools for filtering, transforming, analyzing, and validating CSV data efficiently.

CSV Editor bridges this gap by providing AI assistants with 40+ specialized tools for CSV operations, turning them into powerful data analysts that can:

• Clean messy datasets in seconds
• Perform complex statistical analysis
• Validate data quality automatically
• Transform data with natural language commands
• Track all changes with undo/redo capabilities

# Your AI assistant can now do this:
"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"

# All with automatic history tracking and undo capability!

{
  "mcpServers": {
    "csv-editor": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/jonpspri/csv-editor.git", "csv-editor"],
      "env": {
        "CSV_EDITOR_MAX_FILE_SIZE_MB": "1024",
        "CSV_EDITOR_CSV_HISTORY_DIR": "/tmp/csv_history"
      }
    }
  }
}

{
  "mcpServers": {
    "csv-editor": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/jonpspri/csv-editor.git", "csv-editor"]
    }
  }
}

{
  "cline.mcpServers": {
    "csv-editor": {
      "command": "uvx", 
      "args": ["--from", "git+https://github.com/jonpspri/csv-editor.git", "csv-editor"]
    }
  }
}

{
  "mcpServers": {
    "csv-editor": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/jonpspri/csv-editor.git", "csv-editor"]
    }
  }
}

{
  "experimental.mcp_servers": {
    "csv-editor": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/jonpspri/csv-editor.git", "csv-editor"]
    }
  }
}

# Morning: Load yesterday's data
session = load_csv("daily_sales.csv")

# Clean: Remove duplicates and fix types
remove_duplicates(session_id)
change_column_type("date", "datetime")
fill_missing_values(strategy="median", columns=["revenue"])

# Analyze: Get insights
get_statistics(columns=["revenue", "quantity"])
detect_outliers(method="iqr", threshold=1.5)
get_correlation_matrix(min_correlation=0.5)

# Report: Export cleaned data
export_csv(format="excel", file_path="clean_sales.xlsx")

# Extract from multiple sources
load_csv_from_url("https://api.example.com/data.csv")

# Transform with complex operations
filter_rows(conditions=[
    {"column": "status", "operator": "==", "value": "active"},
    {"column": "amount", "operator": ">", "value": 1000}
])
add_column(name="quarter", formula="Q{(month-1)//3 + 1}")
group_by_aggregate(group_by=["quarter"], aggregations={
    "amount": ["sum", "mean"],
    "customer_id": "count"
})

# Load to different formats
export_csv(format="parquet")  # For data warehouse
export_csv(format="json")     # For API

# Validate incoming data
validate_schema(schema={
    "customer_id": {"type": "integer", "required": True},
    "email": {"type": "string", "pattern": r"^[^@]+@[^@]+\.[^@]+$"},
    "age": {"type": "integer", "min": 0, "max": 120}
})

# Quality scoring
quality_report = check_data_quality()
# Returns: overall_score, missing_data%, duplicates, outliers

# Anomaly detection
anomalies = find_anomalies(methods=["statistical", "pattern"])

• Load & Export: CSV, JSON, Excel, Parquet, HTML, Markdown
• Transform: Filter, sort, group, pivot, join
• Clean: Remove duplicates, handle missing values, fix types
• Calculate: Add computed columns, aggregations

• Statistics: Descriptive stats, correlations, distributions
• Outliers: IQR, Z-score, custom thresholds
• Profiling: Complete data quality reports
• Validation: Schema checking, quality scoring

• Auto-Save: Never lose work with configurable strategies
• History: Full undo/redo with operation tracking
• Sessions: Multi-user support with isolation
• Performance: Stream processing for large files

• Null Value Support: Full support for JSON null → Python None → pandas NaN
• Claude Code Compatible: Handles JSON string serialization automatically
• Type Safety: Improved type annotations with CellValue, RowData, FilterCondition
• Modular Architecture: Organized tool modules for better maintainability

CSV Editor automatically saves your work with configurable strategies:

• Overwrite (default) - Update original file
• Backup - Create timestamped backups
• Versioned - Maintain version history
• Custom - Save to specified location

# Configure auto-save
configure_auto_save(
    strategy="backup",
    backup_dir="/backups",
    max_backups=10
)

git clone https://github.com/jonpspri/csv-editor.git
cd csv-editor
pip install -e .

pipx install git+https://github.com/jonpspri/csv-editor.git

# Install latest version
pip install git+https://github.com/jonpspri/csv-editor.git

# Or using uv
uv pip install git+https://github.com/jonpspri/csv-editor.git

# Install specific version
pip install git+https://github.com/jonpspri/csv-editor.git@v1.0.1

uv run test           # Run tests
uv run test-cov       # With coverage
uv run all-checks     # Format, lint, type-check, test

csv-editor/
├── src/csv_editor/           # Core implementation
│   ├── server.py            # FastMCP server entry point
│   ├── models/              # Data models and session management
│   │   ├── csv_session.py      # Session management & settings
│   │   ├── data_models.py      # Core data types
│   │   └── data_session.py     # Data operations
│   ├── tools/               # MCP tool implementations
│   │   ├── data_io.py          # Load/export operations
│   │   ├── data_manipulation.py # Transform operations
│   │   ├── data_analysis.py     # Statistics & analysis
│   │   └── data_validation.py   # Schema validation
│   ├── exceptions.py        # Custom error handling
│   └── _version.py          # Dynamic version loading
├── tests/                   # Comprehensive test suite
├── examples/                # Usage examples and demos
├── scripts/                 # Maintenance utilities
└── docs/                    # Docusaurus documentation site

1. Type Safety: Full type annotations with Pydantic validation
2. Modularity: Clear separation of concerns across modules
3. Performance: Streaming operations for large datasets
4. Reliability: Comprehensive error handling and logging
5. Usability: Simple installation and configuration
6. Maintainability: Modern tooling and clear documentation

We welcome contributions! See CONTRIBUTING.md for guidelines.

1. Fork the repository
2. Create a feature branch
3. Make your changes with tests
4. Run uv run all-checks
5. Submit a pull request

• SQL query interface
• Real-time collaboration
• Advanced visualizations
• Machine learning integrations
• Cloud storage support
• Performance optimizations for 10GB+ files

• Issues: GitHub Issues
• Discussions: GitHub Discussions
• Documentation: Wiki

Apache 2.0 License - see LICENSE file

Full support for null values across all operations:

# Insert rows with null values
insert_row(session_id, -1, {
    "name": "John Doe",
    "email": null,           # JSON null becomes Python None
    "phone": null,
    "notes": "Contact pending"
})

# Update cells to null
set_cell_value(session_id, 0, "email", null)

# Filter for null values
filter_rows(session_id, [{"column": "email", "operator": "is_null"}])

Automatically handles Claude Code's JSON string serialization:

// Claude Code sends this:
{
  "data": "{\"Company\": \"Acme\", \"Contact\": null, \"Status\": \"Active\"}"
}

// CSV Editor automatically parses it to:
{
  "data": {"Company": "Acme", "Contact": null, "Status": "Active"}
}

Built with:

• FastMCP - Fast Model Context Protocol
• Pandas - Data manipulation
• NumPy - Numerical computing

Ready to supercharge your AI's data capabilities? Get started in 2 minutes →