Docs MCP Server

🚀 Docs - mcp-server

docs-mcp-server is a tool designed to facilitate the setup and management of an MCP server. It provides commands for initialization, server startup, and project building, and supports environment configuration for seamless integration with OpenAI services.

🚀 Quick Start

📦 Installation

Install docs-mcp-server globally using the following command:

npm install -g docs-mcp-server

💻 Usage Examples

Basic Usage

After installation, you can use the command-line tool as follows:

npx docs-mcp-server <command> [options]

Available commands include:

• init: Initialize a new MCP server configuration file.
• serve: Start the MCP server.
• build: Build the project.

For more detailed information, refer to docs-mcp-server --help.

🛠️ Environment Configuration

Create a .env file based on .env.example:

cp .env.example .env

Update your OpenAI API key in the .env file:

# Required: Your OpenAI API key.
OPENAI_API_KEY=your-api-key-here

# Optional: Your OpenAI organization ID (automatically handled by LangChain)
OPENAI_ORG_ID=

# Optional: Custom base URL for the OpenAI API (e.g., for Azure OpenAI or compatible APIs)
OPENAI_API_BASE=

# Optional: Embedding model name (default is "text-embedding-3-small")
# Example: text-embedding-3-large, text-embedding-ada-002
DOCS_MCP_EMBEDDING_MODEL=

# Optional: Specify a custom directory to store the SQLite database file (documents.db).
# If not set, the default behavior is as follows:
# 1. Use './.store/' in the project root directory (if it exists, for legacy versions).
# 2. Fall back to the operating system-specific data directory (e.g., ~/Library/Application Support/docs-mcp-server on macOS).
DOCS_MCP_STORE_PATH=/path/to/your/desired/storage/directory

🚀 Release

This project uses semantic-release and Conventional Commits to automate the release process.

How it works:

1. Commit Messages: All commits merged into the main branch must follow the Conventional Commits specification.
2. Manual Trigger: When you're ready for a new release, you can manually trigger the "Release" workflow from the Actions tab in GitHub.
3. semantic-release Actions: Determine the version number, update CHANGELOG.md and package.json, commit changes, tag the release, publish to npm, and create a GitHub release.

What you need to do:

• Use commit messages in Conventional Commits format.
• Merge your changes into the main branch.
• Manually trigger a new release from the Actions section when you're ready.

Automated processes:

• Changelog update
• Version number adjustment
• Tagging
• npm publishing
• GitHub release creation

🏗️ Project Architecture

For information about the project's architecture and design principles, refer to ARCHITECTURE.md.

Note that most of the code in this project was generated by the AI assistant Cline using the features of this MCP server.