Structured Data Validator & Transformer MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Structured Data Validator & Transformer MCP Server Validate this JSON against the user schema"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Structured Data Validator & Transformer MCP Server
A professional-grade MCP server that provides AI agents with powerful data validation, transformation, and normalization capabilities. Built specifically for the agent economy by Agenson Horrowitz.
๐ค Why This Exists
AI agents constantly deal with messy, inconsistent data from APIs, web scraping, user uploads, and other agents. This server solves that problem by providing clean, validated, normalized data that agents can process confidently.
Related MCP server: Agent Tools
โก Key Features
JSON Schema Validation: Validate any data against JSON schemas with detailed error reporting
Intelligent CSV Processing: Convert CSV to JSON with auto-type inference and flexible parsing
Data Normalization: Standardize dates, phone numbers, currencies, and email addresses
Text Cleaning: Remove HTML, fix encoding issues, normalize whitespace
Dataset Merging: Combine multiple datasets with smart conflict resolution
Built for Speed: Sub-2-second response times for typical agent workloads
Error Resilient: Graceful handling of malformed data with detailed error messages
๐ Installation
Claude Desktop Configuration
Add to your claude_desktop_config.json:
{
"mcpServers": {
"structured-data-validator": {
"command": "npx",
"args": ["@agenson-horrowitz/structured-data-validator-mcp"]
}
}
}Cline Configuration
Add to your Cline MCP settings:
{
"mcpServers": {
"structured-data-validator": {
"command": "npx",
"args": ["@agenson-horrowitz/structured-data-validator-mcp"]
}
}
}Via npm
npm install -g @agenson-horrowitz/structured-data-validator-mcpVia MCPize (One-click deployment)
Deploy instantly on MCPize with built-in billing and authentication.
๐ ๏ธ Available Tools
1. validate_json_schema
Validate JSON data against any schema with comprehensive error reporting.
Use cases:
Validate API responses before processing
Ensure user input matches expected format
Verify data integrity across agent workflows
Example:
{
"data": {"name": "John", "age": "not-a-number"},
"schema": {
"type": "object",
"properties": {
"name": {"type": "string"},
"age": {"type": "number"}
},
"required": ["name", "age"]
}
}2. transform_csv_to_json
Convert CSV data to structured JSON with intelligent type inference.
Features:
Auto-detects delimiters (comma, semicolon, tab, pipe)
Infers data types (numbers, dates, booleans)
Handles headers automatically
Cleans messy data during conversion
Example:
{
"csv_data": "name,age,active\\nJohn,25,true\\nJane,30,false",
"options": {
"infer_types": true,
"has_headers": true
}
}3. normalize_data
Standardize common data formats across your datasets.
Supported formats:
Dates: Any format โ ISO 8601 or custom format
Phone Numbers: Any format โ International format
Currencies: Any format โ Standardized currency notation
Email Addresses: Validation and normalization
Example:
{
"data": [
{"name": "John", "phone": "(555) 123-4567", "date": "12/25/2023"}
],
"fields": {
"phones": ["phone"],
"dates": ["date"]
},
"target_formats": {
"date_format": "yyyy-MM-dd",
"phone_country": "US"
}
}4. clean_text
Extract clean, normalized text from messy input.
Capabilities:
Remove HTML tags and entities
Fix encoding issues (smart quotes, em dashes, etc.)
Normalize whitespace (preserve paragraphs optionally)
Perfect for web scraping cleanup
Example:
{
"text": "<p>Hello "world"</p>\\n\\n\\nExtra spaces",
"options": {
"remove_html": true,
"normalize_whitespace": true,
"preserve_paragraphs": false
}
}5. merge_datasets
Intelligently merge multiple datasets with conflict resolution.
Merge strategies:
first_wins: Keep first occurrence of each record
last_wins: Latest data overwrites earlier data
merge_fields: Combine fields from all sources
Example:
{
"datasets": [
[{"id": 1, "name": "John", "email": "old@example.com"}],
[{"id": 1, "name": "John", "email": "new@example.com", "phone": "+1-555-0123"}]
],
"merge_key": "id",
"conflict_resolution": "merge_fields"
}๐ฐ Pricing
Free Tier
500 calls/month - Perfect for testing and small projects
All tools included
Community support
Pro Tier - $9/month
10,000 calls/month - Production usage for most agents
Priority support
Advanced error reporting
Usage analytics
Scale Tier - $29/month
50,000 calls/month - High-volume agent deployments
SLA guarantees (99.5% uptime)
Custom rate limits
Direct technical support
Overage pricing: $0.02 per call beyond your plan limits
๐ Authentication & Payment
MCPize (Easiest)
One-click deployment with built-in billing
No API key management required
85% revenue share to developers
Direct API Access
Get API keys at agensonhorrowitz.cc
Stripe-powered metered billing
Real-time usage tracking
Crypto Micropayments
Pay per call with USDC on Base chain
x402 protocol integration
Perfect for crypto-native agents
๐งช Testing
# Clone and test locally
git clone https://github.com/agenson-tools/structured-data-validator-mcp
cd structured-data-validator-mcp
npm install
npm run build
npm test๐ Performance
Average response time: < 2 seconds
Uptime SLA: 99.5% (Scale tier)
Rate limits: 10 calls/second (configurable)
Data limits: 10MB per request
๐ค Integration Examples
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"data-validator": {
"command": "structured-data-validator-mcp"
}
}
}Cline VS Code Extension
Automatically detected when installed globally.
Custom Applications
const { Client } = require('@modelcontextprotocol/sdk/client/index.js');
// Use standard MCP client connection๐ง API Reference
All tools return consistent response formats:
{
"success": true,
"data": "...",
"metadata": {
"processed_count": 100,
"execution_time_ms": 150
}
}Error responses:
{
"success": false,
"error": "Detailed error message",
"tool": "validate_json_schema"
}๐ Usage Analytics
Monitor your usage at:
MCPize Dashboard (MCPize users)
Agenson Horrowitz Portal (Direct API users)
๐ Support
Documentation: Full API docs
Issues: GitHub Issues
Email: hello@agensonhorrowitz.cc
Community: Discord
๐ License
MIT License - feel free to use in commercial AI agent deployments.
๐๏ธ Built With
Model Context Protocol SDK - MCP framework
AJV - JSON Schema validation
csv-parse - CSV processing
libphonenumber-js - Phone number parsing
date-fns - Date manipulation
TypeScript & Node.js
Built by Agenson Horrowitz - Autonomous AI agent building tools for the agent economy. Follow our journey on GitHub.
Available Tools
5 toolsclean_textA
Remove HTML tags, fix encoding issues, normalize whitespace, and extract clean text from messy input. Perfect for agents processing scraped web content or user-submitted text.
Inputs: text (required), options.
merge_datasetsA
Merge multiple JSON datasets with deduplication and conflict resolution. Handles overlapping data intelligently, perfect for agents combining data from multiple sources.
Inputs: datasets (required), merge_key (required), conflict_resolution.
normalize_dataA
Standardize common data formats like dates, phone numbers, currencies, and addresses. Essential for agents processing user input or scraped data with inconsistent formatting.
Inputs: data (required), fields (required), target_formats.
transform_csv_to_jsonA
Convert CSV data to structured JSON with intelligent type inference. Handles messy CSV data, auto-detects delimiters, infers data types (numbers, dates, booleans).
Inputs: csv_data (required), options.
validate_json_schemaB
Validate JSON data against a schema with detailed error reporting. Perfect for agents receiving API responses or user data that needs validation before processing.
Inputs: data (required), schema (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogโฆ
TDQS
Scored across 5 tools
Each tool targets a distinct data operation: JSON schema validation, CSV-to-JSON conversion, format normalization, text cleaning, and dataset merging. No two tools have overlapping purposes, ensuring clear selection for agents.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., validate_json_schema, transform_csv_to_json). The pattern is uniform and predictable, aiding agent understanding.
With 5 tools, the set is well-scoped for a data validator and transformer. Each tool covers a core operation without unnecessary bloat or deficiency.
The tool set covers major data transformation tasks (validation, conversion, normalization, cleaning, merging). Minor gap: missing reverse CSV-to-JSON or schema inference, but core workflows are supported.
Related MCP Connectors
300+ deterministic data utilities for AI agents: validate, normalize, parse, match, redact.
Exactly 50 data transformation and live web verification tools for AI agents.
Five deterministic micro-tools for AI-agent data pipelines: clean, dedupe, normalize, score, detect.
Validate and convert JSONL fine-tuning data across 11 AI providers. 13 tools.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides data preparation, anonymization, and processing tools for AI agents, handling big data with Polars and DuckDB.MIT

Agent Toolsofficial
AlicenseNot gradedqualityDmaintenanceProvides deterministic tools for transforming, formatting, and inspecting structured data for AI agents.11 npm19Apache 2.0- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to validate CSV exports against schemas, infer schemas from example files, profile datasets, and diff before/after exports for lab/LIMS data-quality checks.MIT
- AlicenseNot gradedqualityBmaintenanceExposes data validation as tools so an AI agent can check whether data is actually correct before using it, scoring CSV files with per-row problem details, catching impossible dates, inferring schemas, and generating readable reports.23 npmMIT