RAPID

MCP Server: Rapid Alignment of Project Intelligence and Documentation

python

4

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "otdavies-rapid": {
      "command": "python",
      "args": [
        "your-path-here\\\\server.py"
      ]
    }
  }
}

RAPID is a local MCP server that provides fast code analysis and project-wide search capabilities. It uses a high-performance Rust-based file scanner to extract files, functions, and classes from your project, exposing MCP tools you can call from your IDE or AI assistant to understand, navigate, and document your codebase.

How to use

You use the RAPID server by registering it with your MCP client and then invoking its tools to build a contextual understanding of your project. Start with initializing the project context to generate a plan and assess the codebase, then run full code context extraction to collect file structures and function/class descriptions. Use the search tools to locate strings, patterns, or concepts across the entire repository, and leverage the semantic search to find related code by description.

How to install

Prerequisites: install the following on your machine before proceeding.

# Install Git
# https://git-scm.com/downloads

# Install Python 3.8+
# https://www.python.org/downloads/

# Install Rust (uses rustup)
# https://rust-lang.org/tools/install

Clone the RAPID repository and navigate into it.

git clone https://github.com/otdavies/Rapid.git
cd Rapid

Set up a Python virtual environment and install dependencies.

# Create and activate virtual environment
python -m venv venv

# Activate it
# On Windows:
venv\Scripts\activate
# On macOS/Linux:
source venv/bin/activate

# Install dependencies
pip install -r requirements.txt

Build the Rust file scanner that powers the analysis.

c d file_scanner
cargo build --release
cd ..

Additional setup and usage notes

After building, you configure your MCP client to communicate with the RAPID server. The client uses a stdio integration that starts the Python server and keeps the process in sync with your editor.

"mcpServers": {
  "project_context": {
    "disabled": false,
    "timeout": 30,
    "type": "stdio",
    "command": "python",
    "args": [
      "your-path-here\\server.py"
    ],
    "env": {}
  }
}

Available tools

initialize_project_context

Initializes project context by reading/creating plan.md and provides a complexity assessment with guidance for interacting with the codebase. This should be the first tool called when starting work on a project.

get_full_code_context

Comprehensively scans a project directory to extract and structure code from specified file types. Generates a detailed overview of the project's content, including file structures and optionally, function/class descriptions.

search

Global text search across all files in the project to locate strings, code, functions, variables, or configuration values with contextual results.

search_by_concept

AI-powered semantic code search that matches natural language queries to relevant code concepts, enabling concept-based discovery of functionality.