dingdawg-data-agent

dingdawg-data-agent

Breakthrough data pipeline bottlenecks. AI data engineering that learns YOUR schema patterns.

AI-powered data analysis, query building, pipeline design, data quality scoring, and PII detection. Analyze schemas, generate optimized SQL, design ETL pipelines, score data quality, and scan for personally identifiable information. Free tier runs locally. Every action is governed and receipted.

For AI Assistants

This MCP server returns structured JSON for seamless integration:

• PII detection with classification types (SSN, email, phone, address, DOB)
• Data quality scores with specific column-level metrics
• Governance receipt on every call (audit-ready)
• Chain-ready: analyze_data for schema understanding -> data_quality for profiling -> privacy_scan for PII -> query_builder for optimized access -> pipeline_design for ETL orchestration

Composable with any MCP client: Claude Code, Cursor, VS Code, ChatGPT Desktop, Windsurf.

Install

npx dingdawg-data-agent

Claude Code

claude mcp add data -- npx dingdawg-data-agent

Cursor

Add to .cursor/mcp.json:

{"mcpServers": {"data": {"command": "npx", "args": ["dingdawg-data-agent"], "env": {"DINGDAWG_API_KEY": "your-key"}}}}

Full Stack (all 13 agents)

npx dingdawg-setup

Tools

Tool	Free Tier	Paid Tier
analyze_data	10/day, basic schema analysis	Unlimited, LLM-powered with relationship discovery
query_builder	10/day, basic SQL generation	Unlimited, AI-optimized queries with explain plans
pipeline_design	5/day, template-based ETL	Unlimited, AI-designed pipelines with error handling
data_quality	10/day, basic profiling	Unlimited, deep quality scoring with anomaly detection
privacy_scan	10/day, pattern-based PII detection	Unlimited, AI-powered with GDPR/CCPA classification

Pricing

• Free: 10 analyses/day, basic operations
• Pro: $49/mo, 100 calls/day, AI-powered deep analysis
• Pay-as-you-go: $0.25/call, no commitment

Get API key: https://dingdawg.com/developers

Governed

Every call is receipted and auditable. PII scans reference specific data classification categories. Query generation includes injection-safety verification. Pipeline designs include data lineage documentation.

Support

[e-mail] | https://dingdawg.com