Development Practices

by agentience

2 1k downloads Not rated yet MIT license
GitHub

About

Extracts and standardizes development practices from Git workflows, integrating with GitHub and Jira to automate branch validation, version management, and PR preparation tasks.

Details

License
MIT license

Explore

- Validates branch names against a configured naming convention
- Creates branches following feature/, bugfix/, hotfix/, release/, and docs/ formats
- Fetches Jira issue summaries for use in branch names
- Updates Jira issue status when creating branches
- Provides both MCP tools and a CLI interface

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Development Practices
    Command (node, npx, python, etc.) npx
    Arguments
    • Argument 1 -y
    • Argument 2 @highlight/mcp-server

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

1. Clone the repository
2. Create a virtual environment with uv:

   uv venv
source .venv/bin/activate

3. Install the package in development mode:
   uv pip install -e .

Note: If you encounter issues with the mcp-python-sdk dependency, you may need to install it separately or use a workaround specific to your environment.


source .venv/bin/activate

PYTHONPATH=./src python -m unittest discover tests

The server provides the following MCP tools:

1. validate_branch_name: Validates a branch name against the configured convention
2. create_branch: Creates a new branch following the convention
3. get_branch_info: Gets information about a branch

Example:
```python
from mcp.tools import call_tool

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "development practices": {
            "env": {},
            "args": [
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "npx"
        }
    }
}

Linux

{
    "env": [],
    "args": [
        "-y",
        "@highlight/mcp-server"
    ],
    "command": "npx"
}

Macos

{
    "env": [],
    "args": [
        "-y",
        "@highlight/mcp-server"
    ],
    "command": "npx"
}

Windows

{
    "env": [],
    "args": [
        "/c",
        "npx",
        "-y",
        "@highlight/mcp-server"
    ],
    "command": "cmd"
}

1. Create a virtual environment and install the package as described above
2. Install development dependencies:

   uv pip install -e ".[dev]"

3. Run tests:
   # With the virtual environment activated
PYTHONPATH=./src python -m unittest discover tests

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.