mcpField
R
Refactoring MCP Server

Refactoring MCP Server

Local
github.com/marshallyDeveloper Tools5Updated 48w ago
Repository

About Refactoring MCP Server

Refactoring MCP Server exposes Martin Fowler's refactoring catalog to LLMs through a language-agnostic design. Developers can inspect code, analyze code smells, preview changes, and apply refactorings; Python is the available backend described.

Key features

  1. 01List refactorings and parameter contracts
  2. 02Preview changes before applying them
  3. 03Apply refactorings to code
  4. 04Inspect code structure
  5. 05Analyze code smells and suggest refactorings

Use cases

  1. 01Explore applicable refactorings for a codebase
  2. 02Review proposed edits before changing files
  3. 03Apply a method rename or extraction
  4. 04Inspect code structure while planning a refactor

MCP support

The MCP server exposes tools to list, preview, and apply refactorings, inspect code structure, and analyze code. It connects to language backends, with Python documented as the first backend.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "marshally-mcp-refactoring": {
      "command": "uvx",
      "args": [
        "mcp-refactoring"
      ]
    }
  }
}
Run commanduvx mcp-refactoring

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypimcp-refactoring0.1.2

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

mcp-refactoring

An MCP (Model Context Protocol) server that exposes Martin Fowler's refactoring catalog to LLMs through a pluggable, language-agnostic architecture.

Features

  • 71+ Refactorings: Full implementation of Martin Fowler's refactoring catalog
  • Pluggable Architecture: Support for multiple languages (Python first, Ruby/Java/Go planned)
  • Safe by Default: Preview mode shows changes before applying
  • LLM-Optimized: TOON output format for token efficiency

Installation

# Using uvx (recommended)
uvx mcp-refactoring

# Using pip
pip install mcp-refactoring

# Using pipx
pipx install mcp-refactoring

Requirements

  • Python 3.10+
  • A language backend (e.g., molting-cli for Python)

Install the Python backend:

pip install molting-cli

Claude Desktop Configuration

Add to your Claude Desktop config:

{
  "mcpServers": {
    "refactoring": {
      "command": "uvx",
      "args": ["mcp-refactoring"]
    }
  }
}

Available Tools

list_refactorings

List available refactorings with their parameter contracts.

list_refactorings(language="python", category="composing_methods")
preview_refactoring

Preview what changes a refactoring would make (dry-run).

preview_refactoring(
    refactoring="extract-method",
    target="src/order.py::Order::calculate#L10-L15",
    params={"name": "calculate_tax"}
)
apply_refactoring

Apply a refactoring to the codebase.

apply_refactoring(
    refactoring="rename-method",
    target="src/order.py::Order::calc",
    params={"new_name": "calculate_total"}
)
inspect_structure

Get structural information about code.

inspect_structure(path="src/order.py", depth="method")
analyze_code

Analyze code for smells and suggest refactorings.

analyze_code(path="src/order.py", smells=["long-method"])

Target Specification

Each language uses its native conventions:

Python
src/order.py::Order::calculate_total        # Method
src/order.py::Order::calculate_total#L10-L15  # Line range
src/order.py::Order                         # Class

Configuration

Create ~/.mcp-refactoring/config.toml:

[backends.python]
enabled = true
command = "molting"

[backends.ruby]
enabled = false
command = "molting-rb"

Environment variable overrides:

MCP_REFACTORING_PYTHON_COMMAND=/path/to/molting
MCP_REFACTORING_PYTHON_ENABLED=true

Refactoring Categories

Based on Martin Fowler's catalog:

  • Composing Methods: extract-method, inline-method, etc.
  • Moving Features: move-method, extract-class, etc.
  • Organizing Data: encapsulate-field, replace-type-code, etc.
  • Simplifying Conditionals: decompose-conditional, guard-clauses, etc.
  • Simplifying Method Calls: rename-method, add-parameter, etc.
  • Dealing with Generalization: pull-up-method, extract-interface, etc.

Development

# Clone the repository
git clone https://github.com/marshally/mcp-refactoring.git
cd mcp-refactoring

# Install in development mode
pip install -e ".[dev]"

# Run tests
pytest

# Run linter
ruff check .

# Run type checker
mypy src/

License

MIT License - see LICENSE for details.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.