Kelnix Datamind Curator

Name: Kelnix Datamind Curator
Author: kelnix

Connect multiple data sources to query, clean, and standardize information for seamless integration into your workflows.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

Sources.Connect: Connect a new data source for querying, fetching, and context building. Validates connectivity before saving. Use 'mock_crm' for a built-in demo with sample companies, contacts, and d
Sources.List: List all connected data sources with their status and type. Returns source_id, name, type, status, and creation date for each source. Free — no credits consumed.
Sources.Test: Test connectivity to a data source and list available tables. Returns connection status, database version info, and up to 20 table names. Free — no credits consumed.

What data it sees

Do you need an account

No: the server works without sign-in

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 context packages and performing semantic vector searches across indexed records. Protect sensitive data through automated PII redaction while streamlining data exploration using either natural language or SQL queries.

Server tool list (12)

Raw names from tools/list. Only developers need these.

sources.connect	Connect a new data source for querying, fetching, and context building. Validates connectivity before saving. Use 'mock_crm' for a built-in demo with sample companies, contacts, and deals data. Costs 1 credit.
sources.list	List all connected data sources with their status and type. Returns source_id, name, type, status, and creation date for each source. Free — no credits consumed.
sources.test	Test connectivity to a data source and list available tables. Returns connection status, database version info, and up to 20 table names. Free — no credits consumed.
data.query	Query data using natural language or SQL. In 'auto' mode, the system detects whether your query is plain English or SQL. Natural language queries are translated to SQL by Claude Haiku using your schema. Returns columns, rows, the executed SQL, and the mode used. Costs 2 credits.
data.fetch	Fetch raw rows from a specific table with optional filters and pagination. Returns columns, rows, row count, and total available records. Costs 1 credit.
data.search	Semantic vector search across your indexed data using ChromaDB embeddings. Finds records that are semantically similar to your natural language query, even if they don't contain the exact keywords. Data must be indexed first (happens automatically when you use context.build or data.fetch). Costs 2 credits.
pipeline.clean	Clean and standardize data formats — dates to ISO 8601, phones to digits, emails to lowercase, currencies to floats. Auto-detects field types from names and values when rules are not provided. Fills nulls with sensible defaults. Returns cleaned data with transformation stats. Costs 2 credits.
pipeline.deduplicate	Remove duplicate records based on specified key fields or full record hash. When keys are provided, two records are considered duplicates if they have identical values for all specified key fields. Returns deduplicated data with stats. Costs 1 credit.
pipeline.redact_pii	Detect and redact personally identifiable information (PII) from records. Auto-detects emails, phone numbers, SSNs, credit cards, IP addresses, names, and addresses using field name heuristics and regex patterns. Returns redacted data with stats on what was found and removed. Costs 1 credit.
context.build	Build an AI-ready context package from one or more data sources. Fetches schemas, sample data, and relevant records from each source, then assembles them into structured chunks optimized for LLM consumption. Perfect for RAG pipelines. Also indexes data for semantic search. Costs 3 credits.
context.summarize	Generate an AI-powered summary of a dataset with key insights. Uses Claude Haiku to analyze the data and produce a narrative summary, key insights as bullet points, and data quality observations. Costs 2 credits.
credits.check_balance	Check your current credit balance and subscription plan. Returns remaining credits and active plan (free, basic, or pro). Call this before expensive operations to verify you have enough credits. Free — no credits consumed.