codebase-context-dumper
A Model Context Protocol server to dump your codebase into your LLM model
Documentation

codebase-context-dumper MCP Server
A Model Context Protocol (MCP) server designed to easily dump your codebase context into Large Language Models (LLMs).
Why Use This?
Large context windows in LLMs are powerful, but manually selecting and formatting files from a large codebase is tedious. This tool automates the process by:
- Recursively scanning your project directory.
- Including text files from the specified directory tree that are not excluded by `.gitignore` rules.
- Automatically skipping binary files.
- Concatenating the content with clear file path markers.
- Supporting chunking to handle codebases larger than the LLM's context window.
- Integrating seamlessly with MCP-compatible clients.
Usage (Recommended: npx)
The easiest way to use this tool is via `npx`, which runs the latest version without needing a local installation.
Configure your MCP client (e.g., Claude Desktop, VS Code extensions) to use the following command:
{
"mcpServers": {
"codebase-context-dumper": {
"command": "npx",
"args": [
"-y",
"@lex-tools/codebase-context-dumper"
]
}
}
}The MCP client will then be able to invoke the `dump_codebase_context` tool provided by this server.
Features & Tool Details
Tool: `dump_codebase_context`
Recursively reads text files from a specified directory, respecting `.gitignore` rules and skipping binary files. Concatenates content with file path headers/footers. Supports chunking the output for large codebases.
Functionality:
- Scans the directory provided in `base_path`.
- Respects `.gitignore` files at all levels (including nested ones and `.git` by default).
- Detects and skips binary files.
- Reads the content of each valid text file.
- Prepends a header (`--- START: relative/path/to/file ---`) and appends a footer (`--- END: relative/path/to/file ---`) to each file's content.
- Concatenates all processed file contents into a single string.
Input Parameters:
- `base_path` (string, required): The absolute path to the project directory to scan.
- `num_chunks` (integer, optional, default: 1): The total number of chunks to divide the output into. Must be >= 1.
- `chunk_index` (integer, optional, default: 1): The 1-based index of the chunk to return. Requires `num_chunks > 1` and `chunk_index <= num_chunks`.
Output: Returns the concatenated (and potentially chunked) text content.
Local Installation & Usage (Advanced)
If you prefer to run a local version (e.g., for development):
1. Clone the repository:
git clone git@github.com:lex-tools/codebase-context-dumper.git
cd codebase-context-dumper2. Install dependencies:
npm install3. Build the server:
npm run build4. Configure your MCP client to point to the local build output:
{
"mcpServers": {
"codebase-context-dumper": {
"command": "/path/to/your/local/codebase-context-dumper/build/index.js" // Adjust path
}
}
}Contributing
Contributions are welcome! Please see CONTRIBUTING.md for details on development, debugging, and releasing new versions.
License
This project is licensed under the Apache License 2.0. See the LICENSE file for details.
Frequently asked questions
What is codebase-context-dumper?
codebase-context-dumper is A Model Context Protocol server to dump your codebase into your LLM model
How do I install codebase-context-dumper?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is codebase-context-dumper open source?
Yes — it is hosted on GitHub at https://github.com/lex-tools/codebase-context-dumper and has 3 stars.
Related MCP tools
🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.
Enhanced MCP server for interactive user feedback and command execution in AI-assisted development, featuring dual interface support (Web UI and Desktop Application) with intelligent environment detection and cross-platform compatibility.
A powerful Zotero AI and MCP plugin with ChatGPT, Gemini 3.7, Claude Fable 5, Claude Opus 5, DeepSeek V4, Grok, OpenRouter, Kimi k3, GLM 5.3, SiliconFlow, GPT-oss, Gemma 4, Qwen 3.8
Connect your browser to AI models. Just use Dia on Chrome, Arc or Firefox.
文颜 MCP Server 可以让 AI 自动将 Markdown 文章排版后发布至微信公众号。
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP