Kelnix Datamind Curator
@kelnixsolutions
About Kelnix Datamind Curator
AI-Ready Data & Context Engineering API. Connect any data source — PostgreSQL, CRMs, APIs — and get clean, structured, AI-ready data in seconds. Natural language queries, semantic vector search, automated PII redaction, deduplication, and AI-powered context building for RAG pipel
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"kelnix-datamind-curator": {
"url": "https://datamind-api.kelnix.org/stream/mcp/",
"headers": {
"X-API-Key": "YOUR_API_KEY"
}
}
}
}Tools
12Connect 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.
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.
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.
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.
Fetch raw rows from a specific table with optional filters and pagination. Returns columns, rows, row count, and total available records. Costs 1 credit.
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.
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.
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.
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.
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.
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.
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.
Overview
What is Kelnix Datamind Curator?
Kelnix Datamind Curator is an AI-ready data and context engineering API that connects to various data sources, enables natural-language querying, cleans and standardizes data, builds context packages for RAG pipelines, and automatically redacts PII. It is designed for developers and AI agents needing unified, privacy-safe data access.
How to use Kelnix Datamind Curator?
Register for a free API key (25 credits, no credit card), then connect a data source and query using REST or MCP. For MCP clients like Claude Desktop or Cursor, add the server URL and API key to the MCP configuration JSON. Use the built‑in tools (e.g., data.query, pipeline.clean, context.build) by sending HTTP requests to the API endpoints.
Key features of Kelnix Datamind Curator
- Natural language or SQL querying of connected data sources.
- Data cleaning: standardize dates, phones, emails, currencies.
- Automated PII detection and redaction.
- Semantic vector search across indexed data.
- AI‑ready context package building for RAG pipelines.
- Credit‑based billing with free tier and monthly plans.
Use cases of Kelnix Datamind Curator
- Query a CRM or PostgreSQL database using plain English.
- Prepare and deduplicate datasets before feeding them to AI models.
- Redact sensitive information automatically in exported data.
- Build summarised context packages for retrieval‑augmented generation.
- Run semantic search across business records without manual indexing.
FAQ from Kelnix Datamind Curator
How does the credit system work?
Each tool call costs a fixed number of credits. You get 25 free credits on signup; additional credits are sold in packs (e.g., 100 for $8) or via monthly plans (Basic 200/mo $15, Pro 2,000/mo $99).
What data sources are supported?
Currently PostgreSQL and a built‑in Mock CRM. MySQL, CSV, and JSON API support are listed as “coming soon”.
Can I self‑host Kelnix Datamind Curator?
Yes. Clone the repository, create a virtual environment, install the Python dependencies, and run uvicorn app:app with your own keys.
Does it handle PII removal?
Yes, the pipeline.redact_pii tool auto‑detects and redacts personally identifiable information programmatically.
How do I integrate with MCP‑compatible clients?
Add the following to your MCP config: a server entry with "url": "https://datamind-api.kelnix.org/stream/mcp/" and the header "X-API-Key": "dm_YOUR_API_KEY". It works with Claude Desktop, Cursor, VS Code, and Smithery.
More Memory & Knowledge MCP servers
Solomd
zhitongblogA markdown editor — and the bridge to your LLM. Local-first, MIT, ~15 MB. Bundled MCP server lets Claude Code / Codex / Cursor drive your vault directly. 14 AI providers BYOK.
Obsidian MCP Server
cyanheadsRead, write, search, and surgically edit Obsidian vault notes, tags, and frontmatter via MCP. STDIO or Streamable HTTP.
Obsidian MCP Server
StevenStavrakisA simple MCP server for Obsidian
Context7 MCP - Up-to-date Docs For Any Cursor Prompt
upstashContext7 Platform -- Up-to-date code documentation for LLMs and AI code editors
Semantic Scholar MCP Server
YUZongminA FastMCP server implementation for the Semantic Scholar API, providing comprehensive access to academic paper data, author information, and citation networks.
Comments