Skip to content
MCP server

Json Ai MCP

Stdio MCP server for validating, transforming and diffing JSON from AI assistants

Runs locallyStatus and history
Install
Pricing
Open source
Platforms
CLI, self-hosted
Runs
Locally
Version
1.0.10
Listing updated
today

Similar MCP servers

About Json Ai MCP

Json Ai MCP is an open-source MCP server for developer tools. It runs locally on your machine and is started by your AI client.

The README describes this as an MCP server that gives an AI assistant JSON-handling operations. It is installed from PyPI as a stdio transport and can be wired into Claude Desktop or any MCP client through a short config entry that launches it with uvx.

The examples in the README show three tool names, validate_json, transform_json and diff_json, which an assistant can call on demand. The README does not document their parameters or output formats beyond those names, so check the repository before relying on specific behaviour.

It suits developers who want their assistant to check, reshape or compare JSON payloads during a session. The README also covers compliance branding and a separate paid service from the same vendor, which is not part of the server's own functionality.

Install

Run in a terminal

claude mcp add json-ai-mcp -- uvx json-ai-mcp

Add to claude_desktop_config.json

{
  "mcpServers": {
    "json-ai-mcp": {
      "command": "uvx",
      "args": [
        "json-ai-mcp"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "json-ai-mcp": {
      "command": "uvx",
      "args": [
        "json-ai-mcp"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "json-ai-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "json-ai-mcp"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "json-ai-mcp": {
      "command": "uvx",
      "args": [
        "json-ai-mcp"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "json-ai-mcp": {
      "command": "uvx",
      "args": [
        "json-ai-mcp"
      ]
    }
  }
}

Using several servers? Build one config file with the MCP config generator.

Tools this server provides (3)

Taken from the project documentation; the running server may differ.

validate_json
Validates JSON input.
transform_json
Transforms JSON data.
diff_json
Compares JSON documents.

What it does

Stdio transport server
Runs locally over stdio and installs from PyPI as the json-ai-mcp package.
JSON validation tool
The README names a validate_json tool for checking JSON input.
JSON transformation tool
The README names a transform_json tool for reshaping JSON data.
JSON diff tool
The README names a diff_json tool for comparing two JSON documents.
Client configuration example
Includes a claude_desktop_config.json snippet using uvx to launch the server.

Good for

  • Checking that JSON produced by an assistant or script is well-formed
  • Reshaping JSON payloads inside a chat session
  • Comparing two JSON documents to spot changes

Pricing

Open source

MIT-licensed and free to self-host; vendor says it charges per job for separate services.

Json Ai MCP FAQ

How do I install it?

The README gives pip install json_ai_mcp, or launching through uvx json-ai-mcp in an MCP client config.

What is the license?

The README states the repository is MIT-licensed and free to self-host.

Which tools does it expose?

The README's examples mention validate_json, transform_json and diff_json.

Is Json Ai MCP free?

Yes. Json Ai MCP is open source, so you can use and self-host it for free.

How do I add Json Ai MCP to Claude Code?

Run this command in your terminal: claude mcp add json-ai-mcp -- uvx json-ai-mcp

What are the best alternatives to Json Ai MCP?

The closest alternatives to Json Ai MCP are Regex Ai MCP, Jwt Ai MCP, Test Case Generator Ai MCP, Api Test MCP and Api Testing MCP.

Where this comes from

  • Description: written from the project's README and its MCP Registry entry.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers