Check JSON against a JSON Schema with exact paths, and schemas for OpenAI, Claude and Gemini strict.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Use when the user asks whether a JSON Schema is valid, or whether it will work with OpenAI Structured Outputs or function calling with strict: true, Claude structured outputs or strict tool use, or Gemini structured output (response_json_schema), or is writing a tool or function schema, an MCP inputSchema, a response_format, or a schema exported from Zod or Pydantic (signals: "Invalid schema for response_format", "strict mode error", "Claude returns 400 for my schema", "will this schema work with OpenAI", "Gemini ignores maxLength", "additionalProperties false", "all fields must be required"). First checks the schema against its draft: type names like "int", "required": true on a property, misspelt keywords, unresolvable $ref, invalid regex, impossible ranges. Then checks each provider's documented rules: OpenAI (every property in required, additionalProperties false on every object, root an object and not anyOf, no allOf/not/if, at most 5000 properties, 10 levels, 1000 enum values, documented formats only), Claude (additionalProperties false, no minimum/maximum/multipleOf/minLength/maxLength, minItems only 0 or 1, no recursion, at most 24 optional and 16 union-typed parameters per request, regex without lookarounds or backreferences), Gemini (minLength, maxLength, uniqueItems, minProperties and similar are dropped without an error). Returns per provider a verdict (ok, warnings, fails), each issue with its JSON Pointer path, rule, fix and the provider's doc URL, plus a converted copy the provider accepts (optional fields made required and nullable for OpenAI, unsupported constraints moved into descriptions the way the official SDK helpers do), and counts (properties, depth, optional and union-typed parameters). Example: {"schema":{"type":"object","properties":{"city":{"type":"string","maxLength":40},"days":{"type":"integer","minimum":1}},"required":["city"]},"providers":["openai","anthropic"]}. Rules are from each provider's docs, checked 2026-11-18; providers can change them, and very large schemas can still hit unpublished size limits.
The JSON Schema to check, as a JSON object (not a string).
Force a draft: 2020-12, 2019-09, 7, 6 or 4. Default: from $schema, else 2020-12.
Which providers to check. Default: all three.
Include a converted copy for each provider that does not accept the schema as is. Default true.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http jig https://jig.clawhard.com/mcp
Use when the user asks whether a JSON Schema is valid, or whether it will work with OpenAI Structured Outputs or function calling with strict: true, Claude structured outputs or strict tool use, or Gemini structured output (response_json_schema), or is writing a tool or function schema, an MCP inputSchema, a response_format, or a schema exported from Zod or Pydantic (signals: "Invalid schema for response_format", "strict mode error", "Claude returns 400 for my schema", "will this schema work with OpenAI", "Gemini ignores maxLength", "additionalProperties false", "all fields must be required"). First checks the schema against its draft: type names like "int", "required": true on a property, misspelt keywords, unresolvable $ref, invalid regex, impossible ranges. Then checks each provider's documented rules: OpenAI (every property in required, additionalProperties false on every object, root an object and not anyOf, no allOf/not/if, at most 5000 properties, 10 levels, 1000 enum values, documented formats only), Claude (additionalProperties false, no minimum/maximum/multipleOf/minLength/maxLength, minItems only 0 or 1, no recursion, at most 24 optional and 16 union-typed parameters per request, regex without lookarounds or backreferences), Gemini (minLength, maxLength, uniqueItems, minProperties and similar are dropped without an error). Returns per provider a verdict (ok, warnings, fails), each issue with its JSON Pointer path, rule, fix and the provider's doc URL, plus a converted copy the provider accepts (optional fields made required and nullable for OpenAI, unsupported constraints moved into descriptions the way the official SDK helpers do), and counts (properties, depth, optional and union-typed parameters). Example: {"schema":{"type":"object","properties":{"city":{"type":"string","maxLength":40},"days":{"type":"integer","minimum":1}},"required":["city"]},"providers":["openai","anthropic"]}. Rules are from each provider's docs, checked 2026-11-18; providers can change them, and very large schemas can still hit unpublished size limits.
| Argument | Type | Description |
|---|---|---|
| draft | string | Force a draft: 2020-12, 2019-09, 7, 6 or 4. Default: from $schema, else 2020-12. |
| schema* | object | The JSON Schema to check, as a JSON object (not a string). |
| providers | array | Which providers to check. Default: all three. |
| include_converted | boolean | Include a converted copy for each provider that does not accept the schema as is. Default true. |
{
"type": "object",
"required": [
"schema"
],
"properties": {
"draft": {
"enum": [
"2020-12",
"2019-09",
"7",
"6",
"4"
],
"type": "string",
"description": "Force a draft: 2020-12, 2019-09, 7, 6 or 4. Default: from $schema, else 2020-12."
},
"schema": {
"type": "object",
"description": "The JSON Schema to check, as a JSON object (not a string)."
},
"providers": {
"type": "array",
"items": {
"enum": [
"openai",
"anthropic",
"gemini"
],
"type": "string"
},
"maxItems": 3,
"minItems": 1,
"description": "Which providers to check. Default: all three."
},
"include_converted": {
"type": "boolean",
"description": "Include a converted copy for each provider that does not accept the schema as is. Default true."
}
}
}Use when the user asks whether some JSON matches a JSON Schema, or when JSON from a model reply, structured output, tool call, API response or file has to be checked against its schema before it is used or stored (signals: "validate this JSON", "does this match the schema", "which field is wrong", "the model returned bad JSON", "check the tool-call arguments", "why does my parser reject this"). Validates a JSON value (data), or raw model text (json_text: a ```json fence or prose around one JSON value is stripped; a syntax error comes back with line and column), against JSON Schema draft 2020-12, 2019-09, 07, 06 or 04, including $ref/$defs, anyOf/oneOf/allOf, if/then/else, unevaluatedProperties, patterns and formats (email, date-time, date, time, uuid, uri, hostname, ipv4, ipv6, duration). Returns valid true/false, every problem with its JSON Pointer path, keyword, expected and got values, and retry_message: a ready-to-send list of fixes for the model that produced the JSON. Example: {"schema":{"type":"object","properties":{"price":{"type":"number"}},"required":["price","sku"]},"data":{"price":"12.50"}}. Gives the expected answer on 6,018 of 6,227 official JSON-Schema-Test-Suite cases (ajv 8: 5,981); most misses are external $ref URLs, which are not fetched, $dynamicRef, and the idn-email, idn-hostname and iri formats, which are not checked. Not for repairing broken JSON syntax or for checking whether a schema works with OpenAI, Claude or Gemini (jig_check_schema).
| Argument | Type | Description |
|---|---|---|
| data | any | The JSON value to check: object, array, string, number, boolean or null. Use this or json_text. |
| draft | string | Force a draft: 2020-12, 2019-09, 7, 6 or 4. Default: from $schema, else 2020-12. |
| schema* | object |
We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 18, 2026.
| The JSON Schema, as a JSON object (not a string). $schema picks the draft; default 2020-12. |
| json_text | string | Raw text that should contain one JSON value, for example a model reply. Code fences and text around the JSON are stripped. Use this or data. |
| max_errors | integer | Most errors to list (default 50). error_count is always the full count. |
| check_formats | boolean | Check "format" (email, date-time, uuid, uri, ...). Default true. |
{
"type": "object",
"required": [
"schema"
],
"properties": {
"data": {
"anyOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "The JSON value to check: object, array, string, number, boolean or null. Use this or json_text."
},
"draft": {
"enum": [
"2020-12",
"2019-09",
"7",
"6",
"4"
],
"type": "string",
"description": "Force a draft: 2020-12, 2019-09, 7, 6 or 4. Default: from $schema, else 2020-12."
},
"schema": {
"type": "object",
"description": "The JSON Schema, as a JSON object (not a string). $schema picks the draft; default 2020-12."
},
"json_text": {
"type": "string",
"maxLength": 300000,
"description": "Raw text that should contain one JSON value, for example a model reply. Code fences and text around the JSON are stripped. Use this or data."
},
"max_errors": {
"type": "integer",
"maximum": 200,
"minimum": 1,
"description": "Most errors to list (default 50). error_count is always the full count."
},
"check_formats": {
"type": "boolean",
"description": "Check \"format\" (email, date-time, uuid, uri, ...). Default true."
}
}
}