Releases: neverinfamous/sqlite-mcp-server
v2.6.3 - Production/Stable
Full Changelog: v2.6.2...v2.6.3
v2.6.2 - Metadata Update
📦 Metadata Updates
- ✅ Changed development status from Beta to Production/Stable
- ✅ Fixed project URLs to point to correct repository
- ✅ Resolves PyPI 'unverified details' warning
🔧 Technical Changes
- Updated pyproject.toml classifiers
- Fixed GitHub repository links in package metadata
No functional changes - metadata update only.
SQLite MCP Server v2.6.1: Complete JSON Operations Suite
Transform your JSON workflows with 6 powerful new tools and enterprise-grade automation
🆕 What's New in v2.6.1
🎯 JSON Helper Tools (6 New Tools)
Dramatically simplify JSON operations with dedicated, secure tools:
json_insert- Secure JSON data insertion with auto-normalizationjson_update- Path-based JSON updates with validationjson_select- Flexible JSON extraction with multiple output formatsjson_query- Advanced JSON filtering, aggregation, and sortingjson_validate_path- JSONPath validation before operationsjson_merge- Intelligent JSON object merging with conflict resolution
🤖 JSON Auto-Normalization Enhanced
- Configurable strict mode for production environments
- Security-aware normalization with malicious pattern detection
- Automatic Python-style JSON fixes (single quotes,
True/False,None, trailing commas)
🛡️ Parameter Binding Interface
- Enhanced MCP tools with optional
paramsarrays for secure parameter binding - SQL injection prevention using SQLite's built-in parameter binding protection
- Backward compatible - existing queries continue to work unchanged
📦 Automatic Parameter Serialization
- Direct object/array parameters - no more manual
JSON.stringify()required - Seamless integration - dict/list objects automatically serialized to JSON
- Cleaner API for both humans and AI assistants
🧠 Enhanced JSON Error Diagnostics
- Intelligent error categorization - structural, security, encoding issues identified
- Contextual guidance with specific suggestions for fixing complex JSON problems
- Security violation detection with clear messaging for suspicious patterns
📊 By the Numbers
- 73 Tools (up from 69) across 14 Categories (up from 13)
- 6 New JSON Helper Tools for simplified operations
- 5 Major Feature Enhancements across the platform
- Zero Breaking Changes - all existing code continues to work
🚀 Quick Start
# Docker (Recommended)
docker pull writenotenow/sqlite-mcp-server:v2.6.1
docker run -i --rm -v $(pwd):/workspace writenotenow/sqlite-mcp-server:v2.6.1 --db-path /workspace/database.db
# Test all 73 tools
python test_runner.py --quick🎯 JSON Helper Tools Examples
// Insert JSON with auto-normalization
json_insert({
"table": "products",
"column": "metadata",
"data": {"name": "Product", "active": true, "tags": ["new"]}
})
// Update specific JSON paths
json_update({
"table": "products",
"column": "metadata",
"path": "$.pricing.discount",
"value": 15.5
})
// Extract with multiple output formats
json_select({
"table": "products",
"column": "metadata",
"paths": ["$.name", "$.pricing.base_price"],
"output_format": "structured"
})🛡️ Enhanced Security
// Before v2.6.1 - Manual serialization required
write_query({
"query": "INSERT INTO table (data) VALUES (?)",
"params": [JSON.stringify({"key": "value"})]
})
// After v2.6.1 - Automatic serialization!
write_query({
"query": "INSERT INTO table (data) VALUES (?)",
"params": [{"key": "value"}] // Auto-serialized with security checks
})🔧 Migration Guide
v2.6.1 is fully backward compatible! All existing code continues to work unchanged. New features are additive and optional.
To use new JSON Helper Tools:
- Update to v2.6.1:
docker pull writenotenow/sqlite-mcp-server:v2.6.0 - Use new
json_*tools for simplified operations - Enjoy automatic parameter serialization and enhanced security
📚 Documentation
- Complete Documentation - Comprehensive guide with examples
- Quick Start Guide - Get up and running in minutes
- Docker Hub - Container images and deployment guides
🙏 Contributors
Special thanks to the community for feedback and testing that made this release possible!
Full Changelog: v2.5.0...v2.6.0
🛡️ SQLite MCP Server v2.5.0 - Enhanced Security Release
September 21, 2025
🔒 Major Security Enhancement
This release introduces a comprehensive parameter binding interface to prevent SQL injection attacks, further hardening against the type of vulnerability found in the original Anthropic SQLite MCP server implementation.
🛡️ New Parameter Binding Interface
Enhanced Security for All Query Tools:
✅ read_query - Secure SELECT operations with parameter binding
✅ write_query - Protected INSERT/UPDATE/DELETE with parameters
✅ create_table - Safe table creation with parameter support
Usage Example:
🧪 Comprehensive Security Testing
NEW: SQL Injection Protection Test Suite
🎯 11 Attack Vectors Tested - Multiple statements, UNION injection, blind injection, comment-based attacks
🛡️ Parameter Binding Protection - All malicious payloads safely neutralized
📊 Security Assessment - Overall security posture: STRONG
⚡ Quick Validation - Run python tests/test_sql_injection.py to verify protection
🔄 Backward Compatibility
✅ Zero Breaking Changes - All existing queries continue to work
✅ Optional Parameters - Add params array only when needed
✅ Seamless Migration - No code changes required for existing implementations
✅ Performance Benefits - Query plan caching and optimization
📊 Tool Count Correction
Corrected Documentation - Updated all references to show accurate count of 69 tools
Client Display Note - Added explanation for MCP clients showing different counts
Comprehensive Coverage - 69 specialized tools across 13 categories
🚀 What's New
Security Features
🛡️ SQL Injection Prevention - Parameter binding interface
🔒 Attack Vector Testing - Comprehensive security validation
📝 Best Practice Compliance - Follows secure coding standards
⚡ Enhanced Performance - Query optimization and caching
Documentation Updates
📚 Parameter Binding Guide - Complete usage examples and best practices
🔢 Accurate Tool Count - Corrected documentation to show 69 tools
🛡️ Security Documentation - Comprehensive security testing guide
📖 Usage Examples - Secure vs insecure query patterns
Testing Enhancements
🧪 SQL Injection Test Suite - 11 attack vectors with comprehensive coverage
✅ Security Validation - Automated testing for injection protection
📊 Test Results - Clear security posture assessment
🚀 Quick Testing - 30-second validation with --quick flag
📦 Installation & Usage
Docker (Recommended)
Security Testing
Quick Validation
🔗 Resources
📚 Complete Documentation - Full feature reference
🛡️ Security Guide - SQL injection protection testing
🐳 Docker Hub - Container images
📖 Parameter Binding Demo - Interactive security demonstration
🏆 Why This Release Matters
🛡️ Enterprise Security - Production-ready SQL injection protection
🔄 Zero Disruption - Seamless upgrade with full backward compatibility
📊 Accurate Documentation - Corrected tool counts and comprehensive guides
🧪 Validated Protection - Comprehensive testing against real attack vectors
⚡ Performance Benefits - Enhanced query optimization and caching
Full Changelog: v2.4.0...v2.5.0
SQLite MCP Server v2.4.0 - Windows GeomFromText Compatibility + Major Optimizations
SQLite MCP Server v2.4.0 🚀
Released September 19, 2025
🎯 Major Improvements
✅ Windows SpatiaLite Compatibility Resolved
- New Feature: Automatic GeomFromText preprocessing for Windows compatibility
- Smart Conversions: Seamlessly converts GeomFromText calls in INSERT/UPDATE statements
- Zero Breaking Changes: Existing code continues to work unchanged
- Standards Compliant: Uses proper OGC GeomFromText syntax
📦 Massive Container Optimization
- 34% Size Reduction: Compressed container size reduced from 74.1MB to 47.3MB
- Improved Performance: Faster pulls and deployments
- Resource Efficiency: Lower storage and bandwidth requirements
🔧 What's New
Automatic Spatial Function Preprocessing
The server now intelligently converts GeomFromText calls for Windows compatibility:
\\sql
-- These now work seamlessly on Windows:
INSERT INTO spatial_table (geom) VALUES (GeomFromText('POINT(1 2)', 4326));
UPDATE spatial_table SET geom = GeomFromText('POINT(10 20)', 3857) WHERE id = 1;
\\
Automatic Conversions:
- \GeomFromText('POINT(x y)', srid)\ → \MakePoint(x, y, srid)\
- \GeomFromText('POINT(x y z)', srid)\ → \MakePointZ(x, y, z, srid)\ (3D points)
- \GeomFromText('LINESTRING(...)', srid)\ → \GeomFromWKB(GeomFromText(...))\ (complex geometries)
🐳 Docker Images
\\�ash
Latest stable release
docker pull writenotenow/sqlite-mcp-server:latest
docker pull writenotenow/sqlite-mcp-server:v2.4.0
\\
📊 Release Stats
- Container Size: 47.3MB (down from 74.1MB)
- New Features: 1 major (GeomFromText preprocessing)
- Test Coverage: +9 comprehensive test cases
- Breaking Changes: None
- Platform Support: Enhanced Windows compatibility
Full Changelog: v2.3.0...v2.4.0
# 🚀 SQLite MCP Server v2.3.0 - "Testing & Validation"
🎯 Major New Feature: Comprehensive Test Suite
Test all 67 tools in 30 seconds!
This release introduces a complete testing infrastructure that makes it easier than ever to validate your SQLite MCP Server installation and discover the full feature set.
✨ What's New
🧪 Comprehensive Test Suite
- 67 tools tested across 13 feature categories
- Smart environment detection - automatically detects capabilities
- Multi-level testing: Quick (30s), Standard (2-3min), Full (5-10min)
- Professional reporting with clear pass/fail status
🚀 Standalone Test Runner
- No pytest required - runs independently
- Easy CLI interface with multiple options
- CI/CD ready with proper exit codes
- Environment validation before testing
📊 New CLI Commands
# Quick validation (30 seconds)
python test_runner.py --quick
# Standard comprehensive test (recommended)
python test_runner.py --standard
# Full test suite with edge cases
python test_runner.py --full
# Environment check only
python test_runner.py --check-env
# New CLI command (after pip install)
sqlite-mcp-test --quick📚 Enhanced Documentation
- Professional testing guide in
tests/README.md - Updated main README with prominent testing section
- Integration examples for CI/CD pipelines
- Troubleshooting guides for common issues
🔧 Technical Improvements
Test Coverage
- ✅ Core Database Operations (8 tools) - CRUD, schema, transactions
- ✅ JSON Operations (12 tools) - JSONB, validation, extraction
- ✅ Text Processing (8 tools) - Regex, fuzzy matching, similarity
- ✅ Statistical Analysis (8 tools) - Descriptive stats, percentiles
- ✅ Vector/Semantic Search (6 tools) - Embeddings, similarity, hybrid
- ✅ Virtual Tables (6 tools) - CSV, R-Tree, series generation
- ✅ Backup/Restore (3 tools) - Database backup, integrity
- ✅ PRAGMA Operations (4 tools) - Configuration, optimization
⚠️ SpatiaLite Geospatial (8 tools) - Platform dependent- ✅ Enhanced Virtual Tables (4 tools) - Smart CSV/JSON import
- ✅ Vector Optimization (4 tools) - ANN search, clustering
- ✅ MCP Resources/Prompts (4 tools) - Meta-awareness features
Smart Environment Detection
- SQLite version and JSONB support detection
- Python version compatibility checking
- Optional dependencies availability (numpy, requests, Pillow)
- SpatiaLite extension detection (graceful skip if unavailable)
- MCP version reporting
Integration Features
- Pytest compatibility - works alongside existing tests
- Docker support - runs in containerized environments
- Windows/Linux/macOS cross-platform support
- CI/CD integration with proper exit codes
📈 Impact on User Experience
For New Users
- Instant confidence - validate functionality in 30 seconds
- Feature discovery - see all 67 tools in action
- Environment troubleshooting - identify setup issues quickly
For Existing Users
- Upgrade validation - ensure new versions work correctly
- Regression testing - catch issues before they impact workflows
- Professional deployment - enterprise-ready validation tools
For Developers
- Contribution confidence - comprehensive test coverage
- Integration testing - works with existing test infrastructure
- Release validation - automated testing for all features
🐳 Docker Images
Updated Docker images are available:
# Latest version
docker pull writenotenow/sqlite-mcp-server:latest
docker pull writenotenow/sqlite-mcp-server:v2.3.0
# Test in Docker
docker run -i --rm writenotenow/sqlite-mcp-server:v2.3.0 --help📦 Installation & Usage
Quick Start
# Install/upgrade
pip install mcp-server-sqlite
# Test everything works
python test_runner.py --quick
# Expected output:
# 🎉 EXCELLENT: 12/12 tools tested successfully!
# 💡 Your SQLite MCP Server is ready for production use!From Source
git clone https://github.com/neverinfamous/sqlite-mcp-server.git
cd sqlite-mcp-server
pip install -r requirements.txt
python test_runner.py --standard🔄 Migration from v2.2.0
No breaking changes! This is a pure feature addition:
- ✅ All existing functionality unchanged
- ✅ Same MCP tools and APIs
- ✅ Same configuration options
- ✅ Same Docker usage patterns
- ➕ New testing capabilities added
Simply upgrade and enjoy the new testing features!
🎯 Why This Release Matters
This release transforms the SQLite MCP Server from "feature-rich database tool" to "enterprise-ready, professionally tested database solution":
- 🏆 Professional credibility through comprehensive testing
- 📈 Easier adoption with instant validation
- 🔧 Better debugging with environment detection
- 🚀 Production confidence with thorough validation
🙏 Acknowledgments
Thanks to the Model Context Protocol team for the foundational SQLite MCP server that this project extends.
📋 Full Changelog
- ➕ Add comprehensive test suite covering all 67 tools
- ➕ Add standalone test runner with multi-level testing
- ➕ Add smart environment detection and capability validation
- ➕ Add professional testing documentation and guides
- ➕ Add CI/CD integration with proper exit codes
- ➕ Add
sqlite-mcp-testCLI command for easy testing - 🔄 Update all version references to v2.3.0
- 📚 Enhanced README with prominent testing section
- 📚 New comprehensive testing guide in
tests/README.md
Docker Tags: latest, v2.3.0
Python Support: 3.10+
SQLite Support: 3.0+ (3.45+ recommended for JSONB)
Platforms: Windows, Linux, macOS
# 🎉 SQLite MCP Server v2.2.0: Advanced Text Processing
🎉 SQLite MCP Server v2.2.0: Advanced Text Processing
🚀 Major Feature Release
This release introduces a comprehensive Advanced Text Processing toolkit, transforming SQLite MCP Server into a powerful text analysis and processing platform with 67 total tools.
✨ NEW: Advanced Text Processing (8 Tools)
Pattern Extraction & Replacement
regex_extract: PCRE-style regex pattern extraction with capture groups and flagsregex_replace: Text replacement with backreferences and safe preview mode
Similarity & Matching
fuzzy_match: Levenshtein distance similarity matching with configurable thresholdsphonetic_match: Soundex and Metaphone phonetic matching for name variationstext_similarity: Multi-algorithm similarity analysis (Cosine, Jaccard, Levenshtein)
Text Processing & Validation
text_normalize: Multi-operation text normalization (case, Unicode, whitespace, punctuation)advanced_search: Multi-method search combining exact, fuzzy, and phonetic techniquestext_validation: Comprehensive pattern validation (email, phone, URL, custom regex)
🔧 Key Features
- PCRE Regex Support: Full Perl-compatible regex with flags (case-insensitive, multiline, dotall)
- Fuzzy Matching: Intelligent similarity scoring with configurable thresholds
- Phonetic Algorithms: Soundex implementation for sound-alike matching
- Multiple Similarity Metrics: Cosine, Jaccard, and Levenshtein distance calculations
- Safe Preview Modes: Preview destructive operations before execution
- Comprehensive Validation: Email, phone, URL, and custom pattern validation
- Performance Optimized: Configurable limits and efficient algorithms
🐛 Bug Fixes
- Fixed: Duplicate WHERE clause SQL bug in
text_normalizefunction - Improved: Rowid handling for better table compatibility
- Enhanced: Error handling and validation across all text processing functions
📊 Expanded Capabilities
- Total Tools: 67 (59 existing database/analytics + 8 new text processing)
- Pure SQLite: No external dependencies required
- MCP Compatible: Full Model Context Protocol integration
- Enterprise Ready: Production-ready with comprehensive error handling
🔗 Integration Examples
# Extract email addresses with regex
regex_extract(table="contacts", column="info", pattern=r"[\w.-]+@[\w.-]+\.\w+")
# Find similar customer names with fuzzy matching
fuzzy_match(table="customers", column="name", search_term="John Smith", threshold=0.8)
# Validate email addresses in bulk
text_validation(table="users", column="email", validation_type="email")
# Normalize text data with multiple operations
text_normalize(table="reviews", column="comment",
operations=["lowercase", "trim", "remove_extra_spaces"])🎯 Perfect For
- Data Cleaning: Normalize and validate text data
- Fuzzy Matching: Find similar records with typos or variations
- Pattern Extraction: Extract structured data from unstructured text
- Data Validation: Ensure data quality with pattern validation
- Text Analysis: Comprehensive text similarity and phonetic analysis
📈 Performance
- Efficient Algorithms: Optimized for large datasets
- Configurable Limits: Control performance vs accuracy trade-offs
- Memory Optimized: Streaming operations for large text processing
- SQLite Native: Leverages SQLite's performance optimizations
Full Documentation: See README.md for complete feature documentation and examples.
Docker: docker pull ghcr.io/neverinfamous/sqlite-mcp-server:v2.2.0
SQLite MCP Server v2.1.0 - Statistical Analytics Release
SQLite MCP Server v2.1.0 - Statistical Analytics Release
🔬 Major New Feature: Comprehensive Statistical Analysis
This release adds a complete statistical function library with 8 powerful tools for data analysis and business intelligence:
📊 New Statistical Functions:
descriptive_statistics - Complete statistical summary (mean, std dev, variance, quartiles, etc.)
correlation_analysis - Pearson correlation coefficient with relationship interpretation
percentile_analysis - Quartiles, percentiles, and interquartile range calculation
outlier_detection - IQR and Z-score methods for anomaly detection
regression_analysis - Linear regression with slope, intercept, and R² values
hypothesis_testing - One-sample t-tests with statistical significance testing
distribution_analysis - Distribution summary with histogram binning
moving_averages - Time series analysis with trend detection
🎯 Key Benefits:
Advanced Analytics: Professional-grade statistical analysis capabilities
Business Intelligence: Correlation analysis, regression modeling, and trend detection
Data Quality: Outlier detection and distribution analysis for data validation
Scientific Computing: Hypothesis testing with statistical significance
Time Series: Moving averages and trend analysis for temporal data
💡 Example Use Cases:
🔧 Technical Improvements:
Simplified SQL queries for better performance and reliability
Comprehensive error handling and edge case management
Clear, formatted output with statistical interpretation
Full integration with existing MCP framework
🚀 What's Next:
Medium Priority: Advanced text processing with PCRE regex support
🚀 v2.0.0: SpatiaLite Geospatial Analytics Integration
Major Release: Enterprise-Grade GIS Capabilities
✅ NEW FEATURES
SpatiaLite Integration with 7 new geospatial tools
Full Spatial Table Creation and indexing capabilities
Comprehensive Geometry Operations (distance, buffer, area, intersection, union)
Advanced Spatial Analysis (nearest neighbor, spatial joins, clustering)
Shapefile Import capabilities for real-world GIS data
Complete GIS Functionality for location-based business intelligence
🔧 ENHANCEMENTS
Automatic SpatiaLite Extension Loading with Windows DLL support
Persistent Spatial Metadata initialization across connections
Enhanced PATH Management for Windows compatibility
Robust Error Handling for spatial operations
📊 STATISTICS
Total Tools: 51 (was 44)
New Geospatial Tools: 7
Platform Support: Windows ✅, macOS ✅, Linux ✅
🎯 IMPACT
Transforms SQLite into enterprise-grade GIS platform
Enables Sophisticated location-based data analysis
Provides Professional spatial indexing and operations
Supports Complex geospatial business intelligence workflows
📝 USAGE NOTE
Minor limitation with GeomFromText() in INSERT statements has simple workaround documented in README.
SQLite MCP Server v1.9.3 - Enhanced Virtual Tables
🚀 SQLite MCP Server v1.9.3 - Enhanced Virtual Tables
🎯 NEW: Enhanced Virtual Tables (4 New Tools)
✨ Smart CSV Import with Type Inference
create_enhanced_csv_table- Automatic data type detection (INTEGER, REAL, TEXT, DATE)analyze_csv_schema- Deep CSV analysis with statistics and confidence scores- Configurable null value handling and sampling
- Clean column name sanitization for SQL compatibility
✨ JSON Collection Virtual Tables
create_json_collection_table- Support for JSONL and JSON array filesanalyze_json_schema- Comprehensive nested structure analysis- Auto-format detection (JSONL vs JSON arrays)
- Nested object flattening with configurable depth
- Smart schema inference from sample records
🧠 INTELLIGENT FEATURES
- Smart Type Inference Engine: Statistical analysis of sample data
- Flexible Null Handling: Configurable null value patterns
- Nested Data Support: Flatten JSON objects with dot notation
- Performance Optimized: Configurable sampling for large files
- Error Resilient: Graceful handling of malformed data
- Schema Validation: Pre-flight analysis before table creation
📊 ENHANCED CAPABILITIES
- 44 Tools Total (was 40) - 4 new enhanced virtual table tools
- Intelligent Type Detection for CSV numeric, date, boolean patterns
- JSON Structure Analysis with nested object flattening
- File Format Auto-Detection for JSON collections
- Comprehensive Schema Reports with statistics and examples
🎯 PERFECT FOR
- Data Import Workflows: Smart CSV/JSON ingestion with type inference
- Schema Discovery: Analyze file structure before import
- ETL Processes: Automated data type conversion and validation
- Data Analysis: Quick exploration of file-based datasets
- Business Intelligence: Seamless data source integration
🚀 QUICK START
// Analyze CSV structure
analyze_csv_schema({"csv_file_path": "./data.csv"})
// Create table with smart type inference
create_enhanced_csv_table({
"table_name": "imported_data",
"csv_file_path": "./data.csv"
})
// Import JSON collections with flattening
create_json_collection_table({
"table_name": "events",
"json_file_path": "./events.jsonl",
"flatten_nested": true
})Transform any CSV or JSON file into a queryable SQLite table with intelligent type inference!