This release adds 3 notable features for engineering teams evaluating rollout.
Published 3mo
MCP Developer Tools
✓ No known CVEs patched
✓ No known CVEs patched in this version
Topics
code-indexing
code-intelligence
code-search
developer-tools
embeddings
fts5
+7 more
mcp
mcp-server
ollama
python
semantic-search
sqlite
tree-sitter
Summary
AI summaryDocument extractors now index non-code files and PaddleOCR integration adds automatic OCR for scanned PDFs.
Full changelog
What's New
- Document extractors — index non-code files (PDF, DOCX, XLSX, HTML, CSV, email, images, text/RST) alongside source code
- PaddleOCR integration — OCR scanned/image-only PDF pages automatically
- Image OCR — standalone image file OCR with tesseract
- Troubleshooting hint for stale MCP sessions
- Documented git submodule indexing behavior
Install Extras
pip install 'srclight[docs,pdf]' # document formats
pip install 'srclight[pdf,paddleocr]' # + scanned PDF OCR
pip install 'srclight[docs,ocr]' # + image OCR
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About srclight/srclight
Deep code indexing MCP server with SQLite FTS5, tree-sitter, and embeddings. 29 tools for symbol search, call graphs, git intelligence, and hybrid semantic search.
Related context
Beta — feedback welcome: [email protected]