initialize_project_contextLABSCO SUMMARY
Project structure first, so the agent stops guessing.
The intended first move is initialize_project_context, which returns a complexity assessment and guidance along with the plan file; get_full_code_context then fills in the functions and classes underneath. The scanning is Rust rather than Python, which is what makes a whole-project pass something you can repeat rather than do once and cache.
What it is
A local Python server with a Rust file scanner behind it: it walks a project directory, extracts files, functions and classes, and returns that as project context, alongside fast project-wide search.
What you get
- A project initialised from an absolute path, with
plan.mdread or created and a complexity assessment returned - Full code context extracted recursively — files, functions and classes
- Scanning depth, file extensions and output verbosity all configurable
- Fast project-wide search for a string or pattern
- Parsers for Python, Rust, C# and TypeScript/JavaScript
- The file walking and parsing done in Rust, called from the Python server over a C FFI layer
Requirements
Python for the server and the built Rust file-scanner library alongside it. It takes an absolute path to a project directory, so it only reads code on the machine it runs on. The initial scan has a timeout defaulting to 10 seconds, worth raising for large repositories.
Setup effort
Build from source — git clone https://github.com/otdavies/Rapid.git
USE CASES
01
Starting work in an unfamiliar repository
Initialise the project from its absolute path and get a complexity assessment plus the plan file before touching anything.
02
Giving the model the shape of the code
Extract files, functions and classes recursively instead of pasting individual files in.
03
Keeping a large repo within budget
Turn the scanning depth, file extensions and verbosity down so a big project fits the context you have.
04
Finding every place a symbol appears
Run a project-wide search for the string or pattern rather than opening files one at a time.
05
Working in a mixed-language project
Python, Rust, C# and TypeScript/JavaScript all have parsers, so the map covers the whole repo rather than one language.
4 tools
Listed in project docs. Your client may show a different list.
get_full_code_contextsearchsearch_by_conceptBEFORE YOU INSTALL
What to know first
Tools you get
4 tools named in the project's documentation.
Requires
Python
INSTALLATION
Connect your client
This one is built from source rather than installed with a single command.
Server setup
TERMINAL
git clone https://github.com/otdavies/Rapid.git
cd Rapid
python -m venv venv # then activate it
pip install -r requirements.txt
cd file_scanner && cargo build --release && cd ..Add the project-context entry to your MCP client's mcpServers config with the absolute path to server.py
