mcpField
J
JSON Schema Tools

JSON Schema Tools

Local
basitalisandhu.github.ioDeveloper Tools1Updated 2d ago
RepositoryVisit website

About JSON Schema Tools

JSON Schema Tools is an MCP server for developers validating JSON and working with schemas. It supports several schema drafts, sample-based schema inference and change-by-change compatibility assessments.

Key features

  1. 01Validate JSON with Ajv
  2. 02Support drafts 07, 2019-09 and 2020-12
  3. 03Infer schemas from sample documents
  4. 04Diff schemas with compatibility impact

Use cases

  1. 01Check JSON documents against schemas
  2. 02Generate an initial schema from examples
  3. 03Review schema changes for compatibility

MCP support

Exposes `validate_json`, `infer_schema` and `diff_schemas` tools to MCP clients over stdio.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "basitalisandhu-mcp-json-schema-tools": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/basitalisandhu/mcp-json-schema-tools:0.3.0"
      ]
    }
  }
}
Run commanddocker run -i --rm ghcr.io/basitalisandhu/mcp-json-schema-tools:0.3.0

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
ocighcr.io/basitalisandhu/mcp-json-schema-tools:0.3.0

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

json-schema-tools MCP server

Validates JSON against JSON Schema drafts 07, 2019-09 and 2020-12 with Ajv, infers a schema from sample documents, and diffs two schemas with a compatibility verdict per change.

Part of dev-mcp-servers. Stdio transport only; the server never opens a port.

Tools

ToolInputWhat it returns
validate_jsonschema, data, draft?valid, draft used, error count and up to 200 errors with JSON Pointer path, schema path, keyword, message and params. Formats (email, uri, date-time, uuid and more) are checked.
infer_schemasamples (array of documents or a JSON string), enum_threshold?, detect_formats?, title?A draft 2020-12 schema: types unioned across samples, required for keys present in every sample, nested objects, array items, string formats, optional enums.
diff_schemasbefore, afterEvery change with path, before and after values and an impact: breaking, compatible or review, from the point of view of documents valid under before.

Install

Claude Code:

claude mcp add json-schema-tools -- docker run --rm -i ghcr.io/basitalisandhu/mcp-json-schema-tools:0.2.2

Add -s user to make it available in every project. Any client that reads .mcp.json (Claude Code, Claude Desktop, Cursor):

{
  "mcpServers": {
    "json-schema-tools": {
      "command": "docker",
      "args": ["run", "--rm", "-i", "ghcr.io/basitalisandhu/mcp-json-schema-tools:0.2.2"]
    }
  }
}

Pin the version as shown so that an update cannot change what runs in your editor without you noticing. The package is not on npmjs.com yet, so npx does not work; see the repository README for GitHub Packages npm. From a checkout, use "command": "node", "args": ["<path>/packages/json-schema-tools/dist/index.js"] after npm install && npm run build at the repository root.

What it touches

  • Network: None. Remote $ref targets are not fetched.
  • Local files: None.
  • Telemetry: none.

Notes

  • Ajv runs with strict: false so real-world schemas with unknown keywords still validate.
  • Draft-04 and draft-06 schemas are rejected; update $schema or remove it.
  • Schemas and documents can be passed as JSON values or as JSON strings; both are capped at 2 MB.

Build and test

npm install        # at the repository root
npm run build -w @basitalisandhu/mcp-json-schema-tools
npm test -w @basitalisandhu/mcp-json-schema-tools

Tests use node:test and the SDK's in-memory transport; they do not reach the network.

Licence

MIT. See LICENSE.

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.