Development Automation Server MCP server

MCP is a Python server implementing the Model Context Protocol for use with continue.dev. It exposes customizable prompt templates, resources, and tools to enhance your development workflow through integration with language models.

Installation

Prerequisites

Make sure you have the UV package manager installed:

pip install uv

Setting Up the MCP Server

1. Clone the repository:

git clone https://github.com/yourusername/mcp-server.git
cd mcp-server

2. Install dependencies using UV:

uv pip install -r requirements.txt

3. Start the server:

python -m fastmcp

Usage

Working with Prompts

The server provides predefined prompts from markdown files in the prompts folder. You can customize these prompts using variables in the {{variable}} format.

Available prompts include:

• Code review for LLM-generated code
• Code readability checks based on Clean Code principles
• Conversational brainstorming
• Saving brainstorm results as spec files
• Test-driven development from specifications
• Creating detailed project blueprints

Using Resources

Resources provide additional context to the LLMs:

• URL Content Extraction: Convert web content to markdown format
• Library Documentation: Access comprehensive library documentation
• Project Structure: View complete project structure generated by CodeWeaver or Repomix

Leveraging Tools

The MCP server provides several tools to enhance your workflow:

• Web Search: Search the web using Serper
• Search with Summary: Get web search results with summaries via Perplexity.io
• Test Coverage Analysis: Find missing tests in your codebase
• Test Error Collection: Run unit tests and gather error information

Integration with Continue.dev

To connect this MCP server with Continue.dev:

1. Open Continue.dev settings
2. Add a new MCP provider
3. Configure the endpoint to point to your running MCP server
4. Save and start using the enhanced capabilities in your Continue.dev environment

Configuration

You can customize the server behavior by modifying the templates in the prompts folder or by adding new resource providers.

Adding Custom Prompts

Create a new markdown file in the prompts directory with your prompt template. Use the {{variable}} syntax for dynamic content.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "mcp-server-continue" '{"command":"python","args":["-m","mcp_server_continue.main"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "mcp-server-continue": {
            "command": "python",
            "args": [
                "-m",
                "mcp_server_continue.main"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "mcp-server-continue": {
            "command": "python",
            "args": [
                "-m",
                "mcp_server_continue.main"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect