toon-mcp
Enables encoding JSON into compact TOON format and decoding TOON back to JSON, reducing token usage for LLM prompts.
README
TOON MCP Server
A Model Context Protocol (MCP) server that provides tools for encoding and decoding TOON (Token-Oriented Object Notation).
TOON is a compact, human-readable format designed to represent JSON data using significantly fewer tokens, making it ideal for LLM prompts and context optimization.
👉 Learn more about the format at toonformat.dev
Features
This server exposes two core tools to MCP clients (specifically tested with Gemini CLI):
encode_toon: Converts JSON strings into TOON format to save tokens.decode_toon: Converts TOON formatted text back into standard JSON.
Usage
Quick Start with Gemini CLI
To use this server with the Gemini CLI, follow these steps:
-
Install Gemini CLI (if you haven't already):
npm install -g @google/gemini-cli@latest -
Configure the MCP Server: You can register the server by creating or editing your Gemini settings file, typically located at
~/.gemini/settings.json(Global) or.gemini/settings.json(Project-local).Add the following configuration:
{ "mcpServers": { "toon": { "command": "npx", "args": ["-y", "git+https://github.com/kweinmeister/toon-mcp.git"] } } } -
Run Gemini CLI: Start the CLI interface. The tools should now be available to the model.
gemini
Tools
1. encode_toon
Converts JSON data into the compact TOON format.
Parameters:
| Parameter | Type | Default | Description |
|---|---|---|---|
json |
string |
Required | The JSON data (serialized as a string) to encode. |
indent |
number |
2 |
Number of spaces for indentation. |
delimiter |
string |
, |
Delimiter for arrays/rows. Options: , (comma), \t (tab), | (pipe). |
keyFolding |
string |
"off" |
Collapse single-key wrapper chains (e.g., a.b.c). Options: "off", "safe". |
flattenDepth |
number |
Infinity |
Maximum depth to apply key folding. |
replacer |
(string|number)[] |
undefined |
Array of properties to include in the output. |
Example Prompt in Gemini CLI:
"Use the encode_toon tool to convert this JSON into TOON format:
{"users": [{"id": 1, "name": "Alice"}, {"id": 2, "name": "Bob"}]}"
Output:
users[2]{id,name}:
1,Alice
2,Bob
2. decode_toon
Parses TOON formatted text back into standard JSON.
Parameters:
| Parameter | Type | Default | Description |
|---|---|---|---|
toon |
string |
Required | The TOON formatted string to decode. |
strict |
boolean |
true |
Enforce strict validation (e.g., checking declared array lengths). |
expandPaths |
string |
"off" |
Reconstruct dotted keys into nested objects. Options: "off", "safe". |
indent |
number |
2 |
Number of spaces for indentation. |
Transports
This server supports both HTTP Server-Sent Events (SSE) and Standard IO (stdio).
HTTP / SSE (Default)
Useful for remote deployments (like Cloud Run) or web-based MCP clients.
# Starts on port 8080 by default
npm start
# Custom port
npm start -- --port 3000
Stdio
Used by local clients like Gemini CLI.
npm run start:stdio
Development
Installation
git clone https://github.com/kweinmeister/toon-mcp
cd toon-mcp
npm install
Testing
Run the unit tests to ensure the server tools are functioning correctly:
npm test
Debugging with MCP Inspector
You can use the MCP Inspector to inspect and test the server's tools interactively via a web interface.
npx fastmcp inspect index.ts
Building & Linting
# Linting
npx biome check .
# Type checking
npx tsc --noEmit
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.