MCP JSON/YAML/TOML
bitflight-devops/mcp-json-yaml-toml
Leitor/escritor estruturado para dados JSON, YAML, TOML com validação de schema
Ver no GitHubServidor MCP para leitura e modificação segura de arquivos JSON, YAML e TOML com validação de schema e eficiência de tokens. Previne que agentes de IA destruam arquivos estruturados através de uma interface rigorosa e round-trip safe.
Instalação
npx convez-ai bitflight-devops/mcp-json-yaml-toml1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Modificar configurações em arquivos YAML/TOML sem quebrar sintaxe
- Extrair valores específicos de JSON grandes sem carregar arquivo inteiro
- Validar e atualizar dados estruturados com schema enforcement
- Trabalhar com logs JSON e transcrições de IA mantendo integridade
Veredito

Solução prática que endereça um problema real: agentes de IA frequentemente corrompem arquivos estruturados. A abordagem com schema validation e interface token-efficient é sólida, embora limitada a três formatos específicos. Útil para workflows que exigem confiabilidade em modificações de dados.
README
A tradução para o português deste README ainda está na fila.
Stop AI coding tools from breaking your data files. No more grep guesswork, hallucinated fields, or non-schema-compliant data added to files. This MCP server gives AI assistants a strict, round-trip safe interface for working with structured data.
The Problem
AI coding tools often destroy structured data files:
- They grep through huge json, yaml, and toml files (like json logs, or AI transcript files) and guess at keys.
- They hallucinate fields that never existed.
- They use sed and regex that leave files in invalid states.
- They break YAML indentation and TOML syntax.
- They can't validate changes before writing.
The Solution
mcp-json-yaml-toml provides AI assistants with proper tools for structured data:
- Token-efficient: Extract exactly what you need without loading entire files.
- Schema validation: Enforce correctness using SchemaStore.org or custom schemas.
- Safe modifications: Enforced validation on write; preserve comments and formatting.
- Multi-format: JSON, YAML, and TOML through a unified interface.
- Directive-based detection: Support for
# yaml-language-server,#:schema, and$schemakeys in all formats. - Constraint-based guided generation: Native LMQL support for proactive validation of partial inputs.
- Local-First: All processing happens locally. No data ever leaves your machine.
- Transparent JIT Assets: The server auto-downloads
yqif missing and fetches missing schemas from SchemaStore.org for local caching.
[!NOTE]
JSONC Support: Files with
.jsoncextension (JSON with Comments) are fully supported for reading, querying, and schema validation. However, write operations will strip comments due to library limitations.
Getting Started
Prerequisites
- Python ≥ 3.11 installed.
- An MCP-compatible client (Claude Code, Cursor, Windsurf, Gemini 2.0, n8n, etc.).
Installation
The server uses uvx for automatic dependency management and zero-config execution.
AI Agents & CLI Tools
uvx mcp-json-yaml-toml
Claude Code (CLI)
claude mcp add --scope user mcp-json-yaml-toml -- uvx mcp-json-yaml-toml
Other MCP Clients
Add this to your client's MCP configuration:
{
"mcpServers": {
"json-yaml-toml": {
"command": "uvx",
"args": ["mcp-json-yaml-toml"]
}
}
}
[!TIP] See docs/clients.md for detailed setup guides for Cursor, VS Code, and more.
Schema Discovery & Recognition
The server automatically identifies the correct JSON schema for your files using multiple strategies:
- Directives: Recognizes
# yaml-language-server: $schema=...and#:schema ...directives. - In-File Keys: Detects
$schemakeys in JSON and YAML (also supports quoted"$schema"in TOML). - Local IDE Config: Discovers schemas from VS Code/Cursor extension settings and caches.
- SchemaStore.org: Performs glob-based auto-detection against thousands of known formats.
- Manual Association: Use the
data_schematool to bind a file to a specific schema URL or name.
LMQL & Guided Generation
This server provides native support for LMQL (Language Model Query Language) to enable Guided Generation. This allows AI agents to validate partial inputs (e.g., path expressions) incrementally before execution.
- Incremental Validation: Check partial inputs (e.g.,
.data.us) and get the remaining pattern needed. - Improved Reliability: Eliminate syntax errors by guiding the LLM toward valid tool inputs.
- Rich Feedback: Get suggestions and detailed error messages for common mistakes.
[!TIP] See the Deep Dive: LMQL Constraints for detailed usage examples.
Available Tools
| Tool | Description |
|---|---|
data | Get, set, or delete values at specific paths |
data_query | Advanced yq/jq expressions for transformations |
data_schema | Manage schemas and validate files |
data_convert | Convert between JSON, YAML, and TOML |
data_merge | Deep merge structured data files |
constraint_validate | Validate inputs against LMQL constraints |
constraint_list | List available generation constraints |
[!NOTE] Conversion TO TOML is not supported due to yq's internal encoder limitations for complex structures.
Development
Setup
git clone https://github.com/bitflight-devops/mcp-json-yaml-toml.git
cd mcp-json-yaml-toml
uv sync
Testing
ash
Run all tests (coverage included)
uv run pytest
### Code Quality
The project uses `prek` (a Rust-based pre-commit tool) for unified linting and formatting. AI Agents MUST use the scoped verification command:
```bash
# Recommended: Verify only touched files
uv run prek run --files <file edited>
[!IMPORTANT] Avoid
--all-filesduring feature development to keep PR diffs clean and preserve git history.
Project Structure
mcp-json-yaml-toml/
├── packages/mcp_json_yaml_toml/ # Core logic
│ ├── server.py # MCP implementation
│ ├── yq_wrapper.py # Binary management
│ ├── schemas.py # Schema validation
├── .github/ # CI/CD and assets
├── docs/ # Documentation
└── pyproject.toml # Project config
# Run all tests (coverage included)
uv run pytest
Code Quality
The project uses prek (a Rust-based pre-commit tool) for unified linting and formatting. AI Agents MUST use the scoped verification command:
# Recommended: Verify only touched files
uv run prek run --files <file edited>
[!IMPORTANT] Avoid
--all-filesduring feature development to keep PR diffs clean and preserve git history.
Project Structure
graph TD
Repo[mcp-json-yaml-toml]
Repo --> Packages[packages/mcp_json_yaml_toml]
Repo --> Github[.github]
Repo --> Docs[docs]
Repo --> Config[pyproject.toml]
subgraph "Core Logic"
Packages --> Server[server.py<br/>MCP Server & Tools]
Packages --> Schemas[schemas.py<br/>Schema Validation]
Packages --> Constraints[lmql_constraints.py<br/>LMQL Constraints]
Packages --> YQ[yq_wrapper.py<br/>Binary Manager]
Packages --> YAML[yaml_optimizer.py<br/>YAML Anchors]
Packages --> TOML[toml_utils.py<br/>TOML Utils]
Packages --> Conf[config.py<br/>Config Manager]
end
style Packages fill:#f9f,stroke:#333,stroke-width:2px
style Repo fill:#eee,stroke:#333,stroke-width:4px
Token Efficiency Experiment
Two identical Claude Code sub-agents were given the same task: read ~/.claude.json and report every MCP server listed, including command, args, and env vars.
Setup
- Agent A — standard prompt, used the built-in
Readtool - Agent B — same prompt with one line appended:
You must use the mcp__json-yaml-toml for all file interactions.
Both agents used the sonnet model.
Prompts
Agent A prompt:
Read the file ~/.claude.json and report back:
1. Every MCP server listed in the mcpServers section
2. For each server: the command, args, and any env vars configured
Just report the raw findings. Do not summarize or interpret.
Agent B prompt:
Read the file ~/.claude.json and report back:
1. Every MCP server listed in the mcpServers section
2. For each server: the command, args, and any env vars configured
You must use the mcp__json-yaml-toml for all file interactions.
Just report the raw findings. Do not summarize or interpret.
Results
Both agents returned identical findings (8 MCP servers with correct configs).
| Metric | Agent A (Read tool) | Agent B (mcp-json-yaml-toml) |
|---|---|---|
| Total tokens | 37,119 | 28,734 |
| Tool uses | 4 | 2 |
| Duration | 29.3s | 12.7s |
Agent B used 22.6% fewer tokens and completed in 43% of the time with half the tool calls.
Why
The Read tool loads the entire file into context. ~/.claude.json is a large file — the agent had to consume all of it to find the mcpServers section. The MCP server's data_query tool extracted just the mcpServers section directly, keeping the context window small.