JSON MCP Server

What does “JSON” MCP Server do?

The JSON MCP Server is a Model Context Protocol (MCP) server that enables AI assistants and LLMs to interact with, query, and manipulate JSON data sources using standardized tools and operations. By serving as a bridge between AI clients and external JSON-based data, the server enhances development workflows for tasks that require structured data access, advanced querying, or transformation. It supports powerful features such as JSONPath-based queries, filtering with conditions, array and string operations, date and numeric computations, and aggregation. Developers can leverage the server to perform database-like operations, data analysis, and data-driven automation without needing to build custom integrations for each data source.

List of Prompts

No explicit prompt templates are mentioned in the repository or documentation.

List of Resources

No explicit resources are documented in the repository or README. The server operates on external JSON data via URLs, but does not list predefined resources.

List of Tools

• query
  Query JSON data using JSONPath syntax with extended operations.
  Input:

  • url (string): URL of the JSON data source
  • jsonPath (string): JSONPath expression with optional operations

• filter
  Filter JSON data using conditions.
  Input:

  • url (string): URL of the JSON data source
  • jsonPath (string): Base JSONPath expression
  • condition (string): Filter condition

Use Cases of this MCP Server

• Data Analytics on JSON APIs
  Enables developers or LLMs to run complex queries, aggregations, and statistical computations directly on remote JSON API responses, streamlining data analysis workflows.

• Automated Data Transformation
  Automate mapping, filtering, and transformation of large JSON datasets for ETL (Extract, Transform, Load) pipelines, saving developer time on custom scripts.

• Dynamic Dashboard Creation
  Supports the backend for dashboards that need to aggregate and visualize statistics from various JSON endpoints by providing sorting, grouping, and aggregation tools.

• Rapid Prototyping with Live Data
  Allows LLMs or users to quickly query and manipulate live JSON data for proof-of-concept applications or exploratory data analysis.

• Rule-Based Data Filtering
  Empowers developers to filter and extract relevant information from JSON feeds based on dynamic, programmable conditions.

How to set it up

Windsurf

1. Ensure Node.js is installed on your system.
2. Locate your Windsurf configuration file.
3. Add the JSON MCP Server configuration under the mcpServers object:

   {
     "json": {
       "command": "npx",
       "args": [
         "@gongrzhe/server-json-mcp@latest"
       ]
     }
   }
   

4. Save the configuration and restart Windsurf.
5. Verify the server appears in your available MCP servers list.

Claude

1. Make sure Node.js is installed.
2. Open your claude_desktop_config.json file.
3. Insert the following into your configuration:

   {
     "json": {
       "command": "npx",
       "args": [
         "@gongrzhe/server-json-mcp@1.0.3"
       ]
     }
   }
   

4. Save the configuration and restart Claude Desktop.
5. Check that the JSON MCP Server is available.

Cursor

1. Install Node.js if it’s not already installed.
2. Open the Cursor MCP configuration file.
3. Add the following snippet:

   {
     "json": {
       "command": "npx",
       "args": [
         "@gongrzhe/server-json-mcp@latest"
       ]
     }
   }
   

4. Save and restart Cursor.
5. Confirm the MCP server is running via Cursor’s server list.

Cline

1. Install Node.js.
2. Find and edit your Cline MCP configuration.
3. Add:

   {
     "json": {
       "command": "npx",
       "args": [
         "@gongrzhe/server-json-mcp@latest"
       ]
     }
   }
   

4. Save changes and restart Cline.
5. Validate that the server is accessible in Cline.

Securing API Keys

If your JSON endpoints require authentication, set API keys via environment variables and reference them in your server configuration. Example:

{
  "json": {
    "command": "npx",
    "args": [
      "@gongrzhe/server-json-mcp@latest"
    ],
    "env": {
      "API_KEY": "${API_KEY}"
    },
    "inputs": {
      "api_key": "${API_KEY}"
    }
  }
}

Replace ${API_KEY} with your actual environment variable or secret management strategy.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "json": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “json” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Our opinion

JSON MCP Server is a focused and practical MCP server for JSON data processing, offering powerful tools for querying and filtering, but lacks advanced features like prompt templates, explicit resource definitions, and sampling/roots support. It scores well for utility and simplicity, especially for data-centric workflows.

MCP Score: 6/10

MCP Score