Skip to main content

RootMatrix 🧠

Universal token optimization, intelligent context management, and codebase navigation for AI IDEs and MCP servers.

RootMatrix (formerly Context-Gate) is a Model Context Protocol (MCP) server that acts as a "Second Brain" for AI agents (Cursor, Windsurf, Trae, Claude Code). It intercepts file read requests and enforces a strict progressive context strategy, forcing the AI to navigate codebases surgically instead of blindly reading massive raw files.

This prevents context window exhaustion, drastically speeds up AI generation, and eliminates hallucination caused by context noise.


🚀 Installation

Install the package via pip:

pip install rootmatrix

💻 Quick Start & IDE Integration

RootMatrix integrates seamlessly into your favorite AI IDEs with a single command.

Navigate to your project directory and run:

# 1. Initialize the project context constraints
rootmatrix init-project

# 2. Inject the RootMatrix MCP Server into your IDE
rootmatrix init --ide cursor    # Or: windsurf, trae, claude-desktop

Once you restart your IDE, your AI agent will automatically have access to all RootMatrix optimization tools.


🛠️ Key Functionality & MCP Tools

When connected, AI agents automatically use these surgical tools instead of naive file reads:

  • get_project_map: Generates a structural tree representation of the workspace, automatically filtering out noise (node_modules, venv, etc.).
  • read_optimized_file: The default file inspection tool. Uses AST (Tree-sitter and Python native) to strip out inner implementation logic, leaving only imports, classes, signatures, and docstrings. (Slashes a 4k-token file down to ~400 tokens).
  • read_function: Surgically extracts and returns only the code body of a specific function, keeping the rest of the file out of context.
  • search_codebase: Local semantic RAG search powered by ChromaDB. Helps the AI find exact snippets using natural language.
  • find_references: Locates global occurrences of a specific function or class across the workspace to map dependencies safely.
  • get_context_budget: Enforces a strict daily token limit.

🔗 Manual MCP Integration

If you want to manually configure the MCP server for an IDE or AI agent instead of using the CLI, you can add the following configuration to your client's MCP settings file (e.g., mcp.json or cline_mcp_settings.json):

// ~/.cursor/mcp.json
{
  "mcpServers": {
    "rootmatrix": {
      "command": "python",
      "args": ["-m", "rootmatrix.server"]
    }
  }
}
// PROJECT_FOLDER/.vscode/mcp.json
{
  "mcpServers": {
    "rootmatrix": {
      "type": "stdio",
      "command": "python",
      "args": [
        "-m",
        "rootmatrix.server"
      ]
    }
  }
}

Ensure that the Python environment where rootmatrix is installed is accessible in your system's PATH, or provide the absolute path to your Python executable in the "command" field.


⚙️ Requirements

  • Python 3.10+

📄 License

This project is licensed under the MIT License.

Metadata

Release files for rootmatrix 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for rootmatrix 0.1.0
File Size Uploaded
rootmatrix-0.1.0.tar.gz 23.8 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for rootmatrix 0.1.0
File Interpreter ABI Platform
rootmatrix-0.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 44.6 kB

Release files / rootmatrix-0.1.0.tar.gz

Download URL rootmatrix-0.1.0.tar.gz
Size 23.8 kB
Tags Source
SHA-256 checksum
How to use checksums
f9546104bd17f50351139e18083b3285f1120c5e87610b7fa8273dc7d93969a3
BLAKE2b-256 checksum
How to use checksums
ce788abd7de9273200097e8e00f539be3a7eb9544d5feb5696c6c0424b45578f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.14.4

Release files / rootmatrix-0.1.0-py3-none-any.whl

Download URL rootmatrix-0.1.0-py3-none-any.whl
Size 20.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
c17e381af0875793fa86dbf02b336bcce271e88615f1f66c82ae2e6a367168cd
BLAKE2b-256 checksum
How to use checksums
6b43650bceb5a61bb64c169ab266c04a90d90148f201bf05c248ceace074d0c9
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.14.4

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page