# Kelnix Datamind Curator

Connect multiple data sources to query, clean, and standardize information for seamless integration into your workflows. Enhance your retrieval-augmented generation pipelines by building structured c…

## Quick Start

```bash
# Connect this server (installs CLI if needed)
npx -y @smithery/cli@latest mcp add kelnix/kelnix-datamind-curator

# Browse available tools
npx -y @smithery/cli@latest tool list kelnix/kelnix-datamind-curator

# Get full schema for a tool
npx -y @smithery/cli@latest tool get kelnix/kelnix-datamind-curator sources.connect

# Call a tool
npx -y @smithery/cli@latest tool call kelnix/kelnix-datamind-curator sources.connect '{}'
```

## Direct MCP Connection

Endpoint: `https://kelnix-datamind-curator--kelnix.run.tools`

**Optional config:**
- `datamindApiKey` (query) — Your Kelnix DataMind Curator API key. Get one free at https://datamind-api.kelnix.org/docs
- `anthropicApiKey` (query) — Optional Anthropic API key override. If not set, the server uses its own key.

## Tools (12)

- `sources.connect` — Connect a new data source for querying, fetching, and context building.
- `sources.list` — List all connected data sources with their status and type.
- `sources.test` — Test connectivity to a data source and list available tables.
- `data.query` — Query data using natural language or SQL.
- `data.fetch` — Fetch raw rows from a specific table with optional filters and pagination.
- `data.search` — Semantic vector search across your indexed data using ChromaDB embeddings.
- `pipeline.clean` — Clean and standardize data formats — dates to ISO 8601, phones to digits, emails to lowercase, currencies to floats.
- `pipeline.deduplicate` — Remove duplicate records based on specified key fields or full record hash.
- `pipeline.redact_pii` — Detect and redact personally identifiable information (PII) from records.
- `context.build` — Build an AI-ready context package from one or more data sources.
- `context.summarize` — Generate an AI-powered summary of a dataset with key insights.
- `credits.check_balance` — Check your current credit balance and subscription plan.

```bash
# Get full input/output schema for a tool
npx -y @smithery/cli@latest tool get kelnix/kelnix-datamind-curator <tool-name>
```

## Resources

- `datamind://pricing` — Current pricing for DataMind Curator credits.
- `datamind://supported-sources` — Supported data source types and their configuration.

## Prompts (3)

- `explore_data` (source_type, question) — Step-by-step guide to connect a data source and explore its contents.
- `clean_and_prepare` (source_id, table) — Clean, deduplicate, and redact PII from a dataset.
- `build_rag_context` (source_ids, topic) — Build an AI-ready context package for RAG from multiple data sources.