Provides tools for bidirectional conversion between YAML and JSON formats, allowing AI agents to process and generate YAML-formatted data.
Click on "Install 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., "@mcp-json-toolscompare these two JSON objects and show the differences"
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.
mcp-json-tools
An MCP (Model Context Protocol) server that provides JSON and data manipulation tools for AI agents. Designed for use with Claude Code, Claude Desktop, and any MCP-compatible client.
Tools
Tool | Description |
| Validate JSON data against a JSON Schema, returning detailed errors with paths |
| Compare two JSON objects, showing additions, removals, and changes with paths |
| Transform JSON with pick, rename, flatten, and unflatten operations |
| Convert CSV text to a JSON array with configurable headers, delimiters, and type casting |
| Convert a JSON array of objects to CSV text |
| Convert YAML text to JSON |
| Convert JSON text to YAML |
Installation
npm install
npm run buildUsage with Claude Code
claude mcp add json-tools -- node D:/products/mcp-servers/mcp-json-tools/dist/index.jsUsage with Claude Desktop
Add the following to your Claude Desktop configuration file:
Windows: %APPDATA%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"json-tools": {
"command": "node",
"args": ["D:/products/mcp-servers/mcp-json-tools/dist/index.js"]
}
}
}Tool Details
json_validate
Validate JSON data against a JSON Schema. Returns a valid boolean and an array of errors, each with the field path, message, and schema keyword that failed.
Parameters:
data(string) — JSON data to validateschema(string) — JSON Schema to validate against
json_diff
Compare two JSON objects and produce a structured diff. Each difference includes the dot-notation path, the type of change (added, removed, or changed), and the old/new values.
Parameters:
original(string) — Original JSON objectmodified(string) — Modified JSON object
json_transform
Apply transformations to JSON data. Supports four operations:
pick — Extract specific fields by dot-notation paths
rename — Rename top-level keys using a mapping object
flatten — Flatten nested objects into dot-separated keys
unflatten — Restore dot-separated keys into nested objects
Parameters:
data(string) — JSON data to transformoperation(string) — One of: pick, rename, flatten, unflattenfields(string[]) — For pick: field paths to extractmapping(object) — For rename: old-to-new key mappingseparator(string) — For flatten/unflatten: separator character (default: ".")
csv_to_json
Parse CSV text into a JSON array of objects.
Parameters:
csv(string) — CSV text to converthasHeaders(boolean) — Whether the first row is headers (default: true)delimiter(string) — Column delimiter (default: ",")castTypes(boolean) — Auto-cast numbers and booleans (default: false)
json_to_csv
Convert a JSON array of objects to CSV text. Headers are derived from the union of all object keys.
Parameters:
data(string) — JSON array to convertdelimiter(string) — Column delimiter (default: ",")includeHeaders(boolean) — Include header row (default: true)
yaml_to_json / json_to_yaml
Convert between YAML and JSON formats.
Parameters:
yamlText/jsonText(string) — Text to convertindent(number) — Indentation spaces (default: 2)
License
MIT
This server cannot be installed
Resources
Looking for Admin?
Admins can modify the Dockerfile, update the server description, and track usage metrics. If you are the server author, to access the admin panel.