code_reviewLABSCO SUMMARY
Generate the tests, then actually run them.
Plenty of assistants will write you a pytest file; the difference here is that run_tests executes it in an isolated environment with a timeout and hands back coverage, so a generated suite gets checked before you commit it. Everything is passed as code strings rather than file paths, which keeps it self-contained but means you are feeding it snippets, not pointing it at a repository.
What it is
A Python-focused server that closes the loop between reviewing code and proving it works. It runs the standard static analysis stack over a snippet, generates a pytest suite from the code's own AST — happy path, edge cases, exceptions and type checks — then executes that suite in an isolated environment and reports coverage.
What you get
code_reviewruns pylint, flake8, mypy, bandit, radon and AST inspections and returns issues, security findings and complexity metricsgenerate_testsbuilds a pytest suite from a function or class, covering happy path, edge cases, exceptions and type validationrun_testsexecutes tests with a timeout and returns pass/fail, coverage percentage and line coverageformat_codereformats to PEP8 with black or autopep8 at a line length you choose
Requirements
Python 3.8+ and a checkout of the repository — install it with pip install -e . (package neurodev-mcp, version 0.2.0), preferably into a virtualenv, then run python -m neurodev_mcp.server or the neurodev-mcp command. Stdio is the default transport. The analyzers it shells out to are the usual Python toolchain, so they need to be installed alongside it.
Setup effort
Build from source — git clone https://github.com/ravikant1918/neurodev-mcp.git
USE CASES
01
Reviewing a function before you open the pull request
Get quality, style, typing, security and complexity findings from six analyzers in one pass.
02
Getting a test suite for code that has none
Generate pytest cases from the AST, then run them and read the coverage back.
03
Checking a security concern in a snippet
Run the bandit and AST passes over the code and read the vulnerability findings.
04
Cleaning up formatting before review
Reformat to PEP8 at your line length and see what changed.
4 tools
Listed in project docs. Your client may show a different list.
generate_testsrun_testsformat_codeBEFORE YOU INSTALL
What to know first
Tools you get
4 tools named in the project's documentation.
Requires
Python 3.8 or later
Where it runs
Both documented clients run the server on your machine.
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/ravikant1918/neurodev-mcp.git
cd neurodev-mcp
python -m venv .venv
source .venv/bin/activate
pip install -e .MCP Clients
Claude Desktop — local venv
CLAUDE DESKTOP — LOCAL VENV · JSON
{
"mcpServers": {
"neurodev-mcp": {
"command": "<YOUR_PATH_TO_NEURODEV_MCP>/.venv/bin/python",
"args": [
"-m",
"neurodev_mcp.server"
]
}
}
}<YOUR_PATH_TO_NEURODEV_MCP> is the full path of your clone. The command is the Python inside the .venv the steps create, so the installed package is found.
Cline
CLINE · JSON
{
"mcpServers": {
"neurodev-mcp": {
"command": "<YOUR_PATH_TO_NEURODEV_MCP>/.venv/bin/python",
"args": [
"-m",
"neurodev_mcp.server"
]
}
}
}<YOUR_PATH_TO_NEURODEV_MCP> is the full path of your clone. The README's Cline example runs a bare python, which only finds the package when that python is the .venv one, so this block names the .venv Python directly.
