Sponsored by Deepsite.site

Schemacheck Agent

Created By
garyedgingtona month ago
SchemaCheck Agent validates JSON payloads against JSON Schema Draft 7 and 2020-12 standards. Designed for agent-to-agent workflows, it returns structured validation results instantly — including field-level error paths, human-readable summaries, and optionally a corrected payload when repair mode is enabled. Built on the x402 micropayment protocol, each validation call costs $0.005 USDC on Base mainnet — no subscriptions, no API keys, no accounts. Pay per call, settle on-chain.
Content

SchemaCheck Agent

A machine-native paid API for validating JSON payloads against JSON Schema.

Live endpoint: https://projectx402-production.up.railway.app
MCP endpoint: https://projectx402-production.up.railway.app/mcp


What it does

Send a JSON Schema and a JSON payload. Get back a structured validation result: whether the payload is valid, a list of errors with JSONPath locations, a plain-English summary, and optionally a suggested corrected payload.

Built for autonomous agents, backend pipelines, and developers who need reliable, cheap, per-call JSON validation without managing a library dependency.

Supports two access modes:

  • MCP tools via Streamable HTTP — connect any MCP-compatible client directly, fiat billing via MCP-Hive
  • REST + x402 — HTTP endpoint with USDC micropayment on Base mainnet ($0.005/call)

Endpoints

EndpointPaymentRepairLimit
/mcp (MCP Streamable HTTP)Fiat via MCP-HiveYes (validate_schema)None
POST /v1/schema-checkx402 USDC ($0.005)YesNone
POST /v1/schema-check/trialFreeNo32KB request body
GET /healthFree

Add to your MCP client config:

{
  "mcpServers": {
    "schemacheck": {
      "url": "https://projectx402-production.up.railway.app/mcp"
    }
  }
}

Two tools are available: validate_schema (full, with repair) and validate_schema_trial (free, no repair). See docs/agent_quickstart.md for a full Python MCP client example.


Quickstart — trial (no payment)

curl -X POST https://projectx402-production.up.railway.app/v1/schema-check/trial \
  -H "Content-Type: application/json" \
  -d '{
    "json_schema": {
      "type": "object",
      "required": ["name", "email"],
      "properties": {
        "name": {"type": "string"},
        "email": {"type": "string", "format": "email"}
      },
      "additionalProperties": false
    },
    "payload": {
      "name": "Ada Lovelace",
      "email": "not-an-email"
    }
  }'

Response:

{
  "valid": false,
  "errors": [
    {
      "path": "/email",
      "code": "format",
      "message": "'not-an-email' is not a valid email address.",
      "schema_path": "/properties/email/format"
    }
  ],
  "summary": "The payload failed validation. 1 error found.",
  "suggested_payload": null,
  "confidence": 0.9,
  "meta": {
    "strictness": "normal",
    "repair_attempted": false,
    "engine": "jsonschema",
    "schema_draft": "auto"
  }
}

Quickstart — paid endpoint (x402)

The paid endpoint requires an x402 v2 USDC micropayment of $0.005 per call on Base mainnet.

Payment flow:

  1. Send request to POST /v1/schema-check without payment headers.
  2. Receive 402 Payment Required with x402Version=2 and payment details.
  3. Sign and send payment via PAYMENT-SIGNATURE header.
  4. Receive 200 with validation result.

See docs/agent_quickstart.md for a full Python example with x402 payment handling.


Request fields

FieldTypeRequiredDefaultDescription
json_schemaobjectyesJSON Schema document
payloadanyyesThe JSON value to validate
strictnessstringno"normal""strict", "normal", or "lenient"
repairbooleannofalseReturn a suggested corrected payload if possible
explainbooleannotrueInclude plain-English summary

Response fields

FieldTypeDescription
validbooleantrue if payload passes schema validation
errorsarrayStructured validation errors; empty when valid
summarystringPlain-English summary (null if explain=false)
suggested_payloadany / nullCorrected payload suggestion (paid endpoint + repair=true only)
confidencefloatConfidence score 0–1
metaobjectEngine, strictness, and repair metadata

Error codes

required · type · format · enum · additionalProperties · minimum · maximum · minLength · maxLength · pattern · items · oneOf · anyOf · allOf · unknown


Pricing

ModePrice
Trial (/v1/schema-check/trial)Free
Paid (/v1/schema-check)$0.005 USDC per call

Payment is handled via the x402 protocol — an HTTP-native micropayment standard using USDC on Base.


Health check

curl https://projectx402-production.up.railway.app/health
{"status": "ok", "service": "schemacheck-agent", "version": "0.3.0"}

Reporting issues

If you encounter unexpected responses, payment errors, or validation bugs, please open a GitHub issue.

Include:

  • The endpoint called (/v1/schema-check or /v1/schema-check/trial)
  • The request body (redact any sensitive data)
  • The response received
  • The X-Request-ID header value from the response if available

Further reading

Server Config

{
  "mcpServers": {
    "schemacheck-agent": {
      "url": "https://projectx402-production.up.railway.app/sse"
    }
  }
}
Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
Amap Maps高德地图官方 MCP Server
CursorThe AI Code Editor
Tavily Mcp
Playwright McpPlaywright MCP server
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
ChatWiseThe second fastest AI chatbot™
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.
RedisA Model Context Protocol server that provides access to Redis databases. This server enables LLMs to interact with Redis key-value stores through a set of standardized tools.
Baidu Map百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
Y GuiA web-based graphical interface for AI chat interactions with support for multiple AI models and MCP (Model Context Protocol) servers.
Howtocook Mcp基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server,帮你推荐菜谱、规划膳食,解决“今天吃什么“的世纪难题; Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
DeepChatYour AI Partner on Desktop
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
WindsurfThe new purpose-built IDE to harness magic
Serper MCP ServerA Serper MCP Server