feat: MCP - expanded file selector for more supported tabular file formats; auto index for files larger than 10mb
#3278
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- CSV dialects (ssv, tsv, tab and snappy-compressed versions) - Excel - jsonl/ndjson Also, automatically index CSV dialects larger than 10mb
Contributor
There was a problem hiding this comment.
Pull request overview
This PR expands the MCP server's file format support and adds automatic indexing capabilities for improved performance. The server now handles Excel, OpenDocument Spreadsheet, and JSONL/NDJSON files in addition to native CSV formats, with transparent conversion to CSV using qsv's excel and jsonl commands. Files larger than 10MB are automatically indexed for faster processing.
Key changes:
- Added support for Excel (.xls, .xlsx, .xlsm, .xlsb), OpenDocument (.ods), and JSONL (.jsonl, .ndjson) formats with automatic conversion to CSV
- Implemented automatic indexing for CSV files >10MB to improve query performance
- Enhanced file metadata display to show file size and modification date in file listings
Reviewed changes
Copilot reviewed 4 out of 4 changed files in this pull request and generated 10 comments.
| File | Description |
|---|---|
.claude/skills/src/mcp-tools.ts |
Adds file conversion logic for Excel/JSONL formats and auto-indexing for large files (>10MB) |
.claude/skills/src/mcp-filesystem.ts |
Expands allowed file extensions, adds helper methods for conversion detection, updates MIME type mappings, and enhances file listing with metadata |
.claude/skills/README-MCP.md |
Documents the newly supported file formats and auto-conversion features |
.claude/skills/FILESYSTEM_USAGE.md |
Provides detailed explanation of supported formats, conversion process, and auto-indexing behavior |
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
…_MCP_ prefix for all env_vars
All timeout-sensitive operations now have 5-minute protection against indefinite hangs, type safety is improved, and code duplication has been eliminated.
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Issue 1: Cache Entry Timestamp Not Updated on Reuse - Added touchConvertedFile() method to ConvertedFileManager (src/converted-file-manager.ts:133-147) - This method updates the createdAt timestamp when a cached converted file is reused - Called from mcp-tools.ts:351 before reusing a converted file - Ensures actively-used files maintain recent timestamps and won't be prematurely deleted during LIFO cleanup Issue 2: Race Condition in Cache File Operations - Implemented atomic write pattern in saveCache() method (src/converted-file-manager.ts:57-68) - Uses temp file with unique name (includes process.pid and timestamp) + atomic rename - Added stale temp file cleanup in cleanupOrphanedEntries() (src/converted-file-manager.ts:228-252) - Removes temp files older than 1 hour to prevent disk clutter from crashed processes - Prevents cache corruption when multiple qsv operations run concurrently
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.