MCP JSON YAML TOML

Provides token-efficient, schema-aware access to JSON, YAML, and TOML files with safe, validated modifications.

python

5

GitHub Stars

python

Language

2 months ago

First Indexed

3 weeks ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "bitflight-devops-mcp-json-yaml-toml": {
      "command": "uvx",
      "args": [
        "mcp-json-yaml-toml"
      ]
    }
  }
}

You use this MCP server to give AI assistants a safe, schema-aware interface for reading and modifying JSON, YAML, and TOML files. It validates changes, preserves structure and comments when possible, and works locally for reliable, repeatable data edits.

How to use

You interact with the server through an MCP client. Start the server in your development environment, then configure your MCP client to connect either locally (stdio) or via an MCP endpoint if your setup provides one. When you perform data operations, you can get, set, or delete values at specific paths, transform data between formats, and validate against schemas before writing.

How to install

Prerequisites are installed on your machine before you begin.

Install Python (version 3.11 or newer) and ensure it is available on your PATH.

Install a compatible MCP client (for example, UVX-based tools that can run MCP servers). Ensure you have one that can run the mcp-json-yaml-toml server.

Clone or set up your environment to run the server locally via the MCP tooling you use.

Run the server using the MCP tooling as shown in the configuration example.

Configuration and note-worthy details

Configuration focuses on how you connect your MCP client to the server and what tools are available. The server exposes a set of data-oriented tools you can use to read, modify, and convert structured data safely.

Available data operations include getting, setting, or deleting values at paths, performing transformations between JSON, YAML, and TOML, and validating data against schemas before applying changes.

LMQL support enables guided generation with incremental validation of partial inputs so you can iteratively refine queries before execution.

Troubleshooting and tips

If you encounter environment or runtime issues, verify your Python version and that the MCP client can reach the server. Check that the server command and arguments match what your MCP client expects for stdio connections.

Available tools

data

Get, set, or delete values at specific paths within JSON, YAML, or TOML files.

data_query

Apply advanced transformations using yq/jq-like expressions to extract or reshape data.

data_schema

Manage schemas and validate files against those schemas to ensure correctness.

data_convert

Convert between JSON, YAML, and TOML formats while preserving structure.

data_merge

Deep merge two or more structured data files with controlled conflict resolution.

constraint_validate

Validate inputs against LMQL constraints to guide generation with safe boundaries.

constraint_list

List available generation constraints for proactive validation.