Data Recon MCP
MCP Server for Data Reconciliation between MySQL and Snowflake - Validate data integrity during migrations, ETL processes, and ongoing monitoring
Installation
npx data-recon-mcpAsk AI about Data Recon MCP
Powered by Claude Β· Grounded in docs
I know everything about Data Recon MCP. Ask me about installation, configuration, usage, or troubleshooting.
0/500
Reviews
Documentation
Data Recon MCP Server
An MCP (Model Context Protocol) server for data reconciliation between MySQL and Snowflake databases. Enables LLM agents like Claude, Antigravity, and Perplexity to validate data integrity during migrations, ETL processes, and ongoing monitoring.
π Quick Start
Installation
pip install data-recon-mcp
Configuration
Add to your MCP client configuration:
For Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"data-recon": {
"command": "python3",
"args": ["-m", "mcp_server"]
}
}
}
For Antigravity (~/.gemini/antigravity/mcp_config.json):
{
"data-recon": {
"command": "python3",
"args": ["-m", "mcp_server"]
}
}
For Perplexity (MCP Settings):
{
"data-recon": {
"command": "python3",
"args": ["-m", "mcp_server"]
}
}
That's it! Restart your LLM client and start using the tools.
β¨ Features
- All-in-One - Single command starts everything (MCP server + FastAPI backend)
- 23 MCP Tools for comprehensive data reconciliation
- MySQL and Snowflake support
- Async job execution with progress tracking
- SQLite metadata storage - datasource configs persist locally
π§ Advanced Configuration
Using a Centralized Backend
For team environments where you want everyone to share the same datasources:
1. Start the centralized backend:
git clone https://github.com/hindocharaj1997/data-recon-mcp.git
cd data-recon-mcp
pip install -e .
uvicorn data_recon.main:app --host 0.0.0.0 --port 8000
2. Configure clients to use it:
{
"data-recon": {
"command": "python3",
"args": ["-m", "mcp_server"],
"env": {
"FASTAPI_URL": "http://your-server.company.com:8000"
}
}
}
Pre-configured Data Sources
Register data sources via environment variables:
{
"data-recon": {
"command": "python3",
"args": ["-m", "mcp_server"],
"env": {
"DATASOURCE_MYSQL_PROD": "{\"type\":\"mysql\",\"host\":\"localhost\",\"port\":3306,\"username\":\"user\",\"password\":\"pass\",\"database\":\"mydb\"}"
}
}
}
π MCP Tools
| Category | Tools | Description |
|---|---|---|
| Data Source Management | 7 | Add, list, test, remove datasources |
| Discovery & Validation | 7 | Search tables, validate existence, preview data |
| Individual Checks | 4 | Row count, aggregates, schema, sample rows |
| Job Management | 5 | Create/monitor reconciliation jobs |
Key Tools
add_datasource- Register a MySQL or Snowflake connectionsearch_tables- Find tables by patternrun_row_count_check- Compare row counts between source and targetrun_aggregate_check- Compare SUM, AVG, MIN, MAX valuescreate_recon_job- Run comprehensive reconciliation with all checks
ποΈ Architecture
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β LLM Client β
β (Claude, Antigravity, etc.) β
βββββββββββββββββββββββ¬ββββββββββββββββββββββββββββββββββββ
β MCP Protocol (stdio)
βΌ
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β MCP Server β
β (python3 -m mcp_server) β
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ€
β Embedded FastAPI Backend (or external via FASTAPI_URL) β
β βββββββββββββββ βββββββββββββββ βββββββββββββββββββ β
β β SQLite β β MySQL β β Snowflake β β
β β (metadata) β β Connector β β Connector β β
β βββββββββββββββ βββββββββββββββ βββββββββββββββββββ β
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
π§ͺ Development
# Clone and setup
git clone https://github.com/hindocharaj1997/data-recon-mcp.git
cd data-recon-mcp
pip install -e ".[dev]"
# Run tests
pytest
# Start local MySQL for testing
docker compose -f tests/docker-compose.yml up -d
π License
MIT
π€ Contributing
Contributions welcome! Please open an issue first to discuss proposed changes.
