santoshray02/csv-editor

**Stateful CSV editing for AI assistants.** CSV Editor is an MCP server that gives Claude, ChatGPT, Cursor, Windsurf, and other MCP clients a full suite of CSV operations — with sessions, undo/redo, and auto-save built in. Most data MCPs are analyze-only; this one lets the AI *edit*.
🆕 What's new in v2.0.0 (April 2026)
- **FastMCP 3.x** — migrated from FastMCP 2 to 3.2, aligning with MCP spec 2025-11-25.
- **Python 3.11+ required** (was 3.10+). Tested against 3.11 / 3.12 / 3.13 / 3.14.
- **--transport sse removed.** Use --transport http (Streamable HTTP) for remote deployments. SSE was deprecated by FastMCP 3.
- Dependency refresh: pydantic 2.13, pyarrow 23, httpx 0.28.
- New CSV_EDITOR_CSV_HISTORY_DIR env var for configuring the history directory.
- First-class CI test matrix on GitHub Actions.
Users who pinned csv-editor>=1,
Claude Desktop (click to expand)
Add to your claude_desktop_config.json:
- **macOS:** ~/Library/Application Support/Claude/claude_desktop_config.json
- **Windows:** %APPDATA%\Claude\claude_desktop_config.json
- **Linux:** ~/.config/Claude/claude_desktop_config.json
Claude Code, Cursor, Windsurf, VS Code Copilot, Cline, Continue, Zed
Any MCP-capable client works with stdio transport. See MCP_CONFIG.md for per-client setup.
ChatGPT Connectors (remote HTTP)
ChatGPT Connectors require remote Streamable HTTP with OAuth, which is tracked on the roadmap but not yet in v2.0.0. Use stdio-based clients (Claude Desktop, Claude Code, Cursor, etc.) in the meantime.
💡 Real-World Use Cases
📊 Data Analyst Workflow
🏭 ETL Pipeline
🔍 Data Quality Assurance
🎨 Core Features
Data Operations
- **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
Analysis Tools
- **Statistics**: Descriptive stats, correlations, distributions
- **Outliers**: IQR, Z-score, custom thresholds
- **Profiling**: Complete data quality reports
- **Validation**: Schema checking, quality scoring
Productivity Features
- **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
📚 Available Tools
Complete tool list (39 tools)
Server info (2)
- health_check — health status + active session count
- get_server_info — capabilities, supported formats, limits
I/O operations (7)
- load_csv — Load from file
- load_csv_from_url — Load from URL
- load_csv_from_content — Load from string
- export_csv — Export to various formats (csv, tsv, json, excel, parquet, html, markdown)
- get_session_info — Session details
- list_sessions — Active sessions
- close_session — Cleanup
Data manipulation (10)
- filter_rows — Complex filtering
- sort_data — Multi-column sort
- select_columns — Column selection
- rename_columns — Rename columns
- add_column — Add computed columns
- remove_columns — Remove columns
- update_column — Update values
- change_column_type — Type conversion
- fill_missing_values — Handle nulls
- remove_duplicates — Deduplicate
Analysis (7)
- get_statistics — Statistical summary
- get_column_statistics — Column stats