mcp-json-tools
An MCP server that provides tools for JSON validation, diffing, and transformation operations such as flattening and renaming. It also enables data format conversion between JSON, CSV, and YAML to streamline data processing for AI agents.
README
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 |
|---|---|
json_validate |
Validate JSON data against a JSON Schema, returning detailed errors with paths |
json_diff |
Compare two JSON objects, showing additions, removals, and changes with paths |
json_transform |
Transform JSON with pick, rename, flatten, and unflatten operations |
csv_to_json |
Convert CSV text to a JSON array with configurable headers, delimiters, and type casting |
json_to_csv |
Convert a JSON array of objects to CSV text |
yaml_to_json |
Convert YAML text to JSON |
json_to_yaml |
Convert JSON text to YAML |
Installation
npm install
npm run build
Usage with Claude Code
claude mcp add json-tools -- node D:/products/mcp-servers/mcp-json-tools/dist/index.js
Usage 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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.