This release includes 1 breaking change for platform teams planning a safe upgrade.
✓ No known CVEs patched in this version
Topics
+14 more
Affected surfaces
Summary
AI summaryFixed correlation matrix failures on datasets containing NaN values.
Full changelog
MCP Analytics v1.0.3
Release Notes
Stability improvements and bug fixes following customer feedback from v1.0.2 deployment.
Changes
- Fixed edge case in preprocessing pipeline for datasets with mixed types
- Improved error messages for authentication failures
- Optimized Docker container startup time by 40%
- Enhanced semantic search accuracy for tool discovery
- Resolved memory leak in long-running analysis jobs
- Updated dependencies to latest security patches
Performance Improvements
- Reduced API response time by 25% through caching optimization
- Improved handling of concurrent requests
- Better memory management for large datasets
Bug Fixes
- Fixed issue where correlation matrix would fail on datasets with NaN values
- Resolved OAuth token refresh edge case
- Corrected visualization rendering for time series with irregular intervals
- Fixed CSV parsing for files with non-standard delimiters
Documentation
- Updated API documentation with clearer examples
- Added troubleshooting section to README
- Improved error code reference guide
Compatibility
- Requires Node.js 18.0 or higher
- Compatible with Claude Desktop 0.7.0+
- Tested with Cursor 0.42.0+
For support, contact [email protected]
Copyright 2024 PeopleDrivenAI LLC (DBA EmbeddedLayers)
Breaking Changes
- Requires Node.js 18.0 or higher
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 embeddedlayers/mcp-analytics
Statistical analysis, forecasting, and ML for business data (Shopify, Stripe, WooCommerce, eBay, GA4, Search Console). Upload a CSV or connect live data sources — ask a question in Claude or Cursor, get an interactive HTML report.
Related context
Beta — feedback welcome: [email protected]