JSON MCP Server
Enables reading, writing, and deleting JSON values using dot-notation paths, with automatic creation of files and nested objects.
README
JSON MCP Server
A powerful MCP (Model Context Protocol) server for editing and managing JSON files with dot-notation path access.
Features
- ✅ Read JSON values using dot-separated paths
- ✏️ Set or update JSON values (supports nested structures)
- 🗑️ Delete JSON key-value pairs
- 🔄 Auto-create missing JSON files
- 🌳 Automatically create intermediate nested objects
Installation
# Activate virtual environment
source venv/bin/activate
# Install dependencies
pip install -r requirements.txt
Running the Server
python mcp_json.py
The server runs on stdio transport by default, which is the standard for MCP clients like Claude Desktop.
Tools
1. json:get - Get Value
Retrieve a value from a JSON file using a dot-separated key path.
Parameters:
path: JSON file path (absolute or relative)key: Dot-separated key path (e.g.,"user.name")
Examples:
json:get(path="data.json", key="name")
json:get(path="config.json", key="database.host")
json:get(path="users.json", key="users.0.name")
2. json:set - Set Value
Set or update a value in a JSON file. Supports JSON strings or plain strings. Automatically creates missing intermediate objects.
Parameters:
path: JSON file pathkey: Dot-separated key pathvalue: Value to set (can be JSON string)
Examples:
json:set(path="data.json", key="name", value="John Doe")
json:set(path="config.json", key="port", value="3000")
json:set(path="config.json", key="database", value='{"host":"localhost","port":5432}')
json:set(path="data.json", key="tags", value='["python","mcp","json"]')
json:set(path="config.json", key="api.endpoints.users", value="/api/v1/users")
3. json:delete - Delete Key
Delete a key from a JSON file using a dot-separated key path.
Parameters:
path: JSON file pathkey: Dot-separated key path
Examples:
json:delete(path="data.json", key="oldField")
json:delete(path="config.json", key="database.password")
json:delete(path="user.json", key="settings.theme")
Usage Examples
Example 1: Create User Configuration
json:set(path="user.json", key="profile.name", value="John Doe")
json:set(path="user.json", key="profile.email", value="john@example.com")
json:set(path="user.json", key="profile.age", value="30")
json:set(path="user.json", key="settings.theme", value="dark")
json:set(path="user.json", key="settings.notifications", value="true")
json:get(path="user.json", key="profile")
Result user.json:
{
"profile": {
"name": "John Doe",
"email": "john@example.com",
"age": "30"
},
"settings": {
"theme": "dark",
"notifications": "true"
}
}
Example 2: Manage API Configuration
json:set(path="api.json", key="api.baseUrl", value="https://api.example.com")
json:set(path="api.json", key="api.version", value="v2")
json:set(path="api.json", key="api.timeout", value="5000")
json:set(path="api.json", key="endpoints", value='{"users":"/users","posts":"/posts"}')
json:get(path="api.json", key="api")
json:delete(path="api.json", key="endpoints.posts")
Example 3: Working with Arrays
json:set(path="tasks.json", key="tasks", value='[{"id":1,"title":"Learn MCP","done":false}]')
json:get(path="tasks.json", key="tasks.0.title")
MCP Client Configuration
Add this server to your MCP client (e.g., Claude Desktop):
{
"mcpServers": {
"json-editor": {
"command": "python3",
"args": ["/absolute/path/to/mcp_json.py"],
"enabled": true
}
}
}
Or using the virtual environment Python:
{
"mcpServers": {
"json-editor": {
"command": "/absolute/path/to/venv/bin/python",
"args": ["/absolute/path/to/mcp_json.py"],
"enabled": true
}
}
}
How It Works
- Dot-notation paths: Use dots (
.) to separate nested keys:"user.profile.name" - Auto-creation: Missing files are created as empty objects
{} - Nested objects: Missing intermediate objects are automatically created
- Value parsing: The
valueparameter attempts JSON parsing first, falls back to string - Pretty formatting: JSON files are saved with 2-space indentation
Error Messages
❌ Key not found: {key}- When trying to get or delete a non-existent keyInvalid JSON format: {path}- When the file exists but contains invalid JSON
Development
The server uses FastMCP, which provides:
- Automatic parameter validation
- Built-in error handling
- Support for multiple transports (stdio, SSE, HTTP)
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.