mcpField
K
Kelnix Datamind Curator

Kelnix Datamind Curator

Remote
github.com/kelnixsolutionsMemory & Knowledge0Updated 33w ago
Repository

About Kelnix Datamind Curator

Kelnix Datamind Curator is an API for connecting data sources and preparing structured data and context for AI agents. It combines querying, data cleanup, semantic search, deduplication, PII redaction, and RAG context building.

Key features

  1. 01Connect and inspect data sources
  2. 02Query with natural language or SQL
  3. 03Fetch rows with filters and pagination
  4. 04Semantic vector search
  5. 05Standardize, deduplicate, and redact data
  6. 06Build context and summarize datasets

Use cases

  1. 01Query connected data for an AI agent
  2. 02Search indexed data semantically
  3. 03Clean records and remove duplicates
  4. 04Prepare context for RAG pipelines

MCP support

Provides MCP clients with tools for managing sources, querying and searching data, cleaning records, redacting PII, and building context. Its MCP endpoint is configured with an API key.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://datamind-api.kelnix.org/stream/mcp/
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
Streamable HTTPhttps://datamind-api.kelnix.org/stream/mcp/Auth required

Tools

12
ParameterTypeRequiredDescription
source_typestringYesType of data source to connect. Supported: postgresql, mysql, csv, json_api, mock_crm
namestringYesA friendly name for this data source (e.g. 'Production DB', 'Salesforce CRM')
connection_stringanyNoDatabase connection string (e.g. 'postgresql://user:pass@host:5432/db'). Required for database sources.
configanyNoAdditional config as key-value pairs (e.g. API URL, headers, file path). Source-type specific.

Details

From the project README

Kelnix DataMind Curator

Kelnix DataMind Curator

🧠 AI-Ready Data & Context Engineering API
Connect any data source, query with natural language, clean and standardize data, build AI-ready context packages, and protect privacy with automated PII redaction.

📖 API Docs • 💰 Pricing • 🌐 Website

Glama MCP Server Badge


One API to unify, clean, and serve your data to AI agents. ⚡

🚀 Quick Start

# 1. Register (free — 25 credits, no credit card)
curl -X POST https://datamind-api.kelnix.org/register \
  -H "Content-Type: application/json" \
  -d '{"agent_name": "My Agent"}'

# 2. Connect a data source (mock CRM for demo)
curl -X POST https://datamind-api.kelnix.org/sources/connect \
  -H "X-API-Key: dm_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"source_type": "mock_crm", "name": "Demo CRM"}'

# 3. Query with natural language
curl -X POST https://datamind-api.kelnix.org/data/query \
  -H "X-API-Key: dm_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"source_id": "YOUR_SOURCE_ID", "query": "top 5 companies by revenue"}'

🔌 MCP Integration

Works with Claude Desktop, Cursor, VS Code, and any MCP-compatible client.

Claude Desktop / Cursor

Add to your MCP config:

{
  "mcpServers": {
    "kelnix-datamind-curator": {
      "url": "https://datamind-api.kelnix.org/stream/mcp/",
      "headers": {
        "X-API-Key": "dm_YOUR_API_KEY"
      }
    }
  }
}
Smithery
npx -y @smithery/cli@latest install @kelnix/kelnix-datamind-curator --client claude

🛠️ Tools

ToolDescriptionCost
sources.connect🔗 Connect a data source (PostgreSQL, MySQL, CRM, API)1 credit
sources.list📋 List connected data sourcesfree
sources.test✅ Test source connectivityfree
data.query💬 Query data with natural language or SQL2 credits
data.fetch📥 Fetch raw rows with filters & pagination1 credit
data.search🔍 Semantic vector search across indexed data2 credits
pipeline.clean🧹 Standardize dates, phones, emails, currencies2 credits
pipeline.deduplicate🔄 Remove duplicate records1 credit
pipeline.redact_pii🔒 Auto-detect and redact PII1 credit
context.build🧠 Build AI-ready context for RAG pipelines3 credits
context.summarize📊 AI-powered dataset summary with insights2 credits
credits.check_balance💳 Check credits and planfree

📦 Supported Data Sources

  • 🐘 PostgreSQL — Full SQL support with schema introspection
  • 🐬 MySQL — Coming soon
  • 🏢 Mock CRM — Built-in demo with companies, contacts, and deals
  • 📄 CSV — Coming soon
  • 🌐 JSON API — Coming soon

💰 Pricing

CreditsPricePer Credit
25🎁 Freeon signup
100$8$0.080
500$30$0.060
1,000$50$0.050
5,000$200$0.040
10,000$400$0.040

Monthly plans: Basic (200/mo, $15) · Pro (2,000/mo, $99)

💳 Pay with Stripe (cards) or 🪙 300+ cryptocurrencies.

📖 API Docs

Interactive Swagger docs: datamind-api.kelnix.org/docs

🏗️ Self-Hosting

git clone https://github.com/kelnixsolutions/Kelnix-DataMind-Curator.git
cd Kelnix-DataMind-Curator
python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
cp .env.example .env  # edit with your keys
uvicorn app:app --host 0.0.0.0 --port 8001

🏛️ Architecture

┌──────────────┐     ┌──────────────┐     ┌──────────────┐
│  MCP Clients │     │  REST API    │     │  Registries  │
│ Claude/Cursor│────▶│  FastAPI     │◀────│ Smithery/etc │
└──────────────┘     └──────┬───────┘     └──────────────┘
                            │
                 ┌──────────┼──────────┐
                 │          │          │
          ┌──────▼──┐ ┌────▼────┐ ┌───▼──────┐
          │Connectors│ │Pipeline │ │ Context  │
          │ PG/CRM  │ │Clean/PII│ │Build/NLQ │
          └─────────┘ └─────────┘ └──────────┘
                 │          │          │
          ┌──────▼──┐ ┌────▼────┐ ┌───▼──────┐
          │ SQLite  │ │ Redis   │ │ ChromaDB │
          │ Billing │ │ Cache   │ │ Vectors  │
          └─────────┘ └─────────┘ └──────────┘

📜 License

MIT — Kelnix Solutions

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.