Raul Pino p1nox

Custom MCP servers for Claude Desktop and Claude Code in macOS

Using mcp-remote as a proxy to remote MCP server.

Desktop

Add/Edit your local mcp json file for claude tools:

vim /Users//Library/Application\ Support/Claude/claude_desktop_config.json

# install
pip install notebook

# launch
jupyter notebook

# jupyter remote access with password - https://towardsdatascience.com/how-to-share-your-jupyter-notebook-in-3-lines-of-code-with-ngrok-bfe1495a9c0c
sudo snap install ngrok
ngrok config add-authtoken xyz

After researching a lot on how to use PyTorch with a RTX 3060 card, specially with older versions or torch (0.4.0) and torchvision (0.2.1), I noticed that it was either impossible or very hard to do. RTX 3060 and these packages apparently doesn't have compatibility with the same versions of CUDA and cuDNN. I tried to do this by using different combinations with compiled versions available in conda, but didn't work, maybe it could work if you recompile from source these versions.

After all this, actually I was able to use RTX 3060 effectively with latest versions of all these dependencies with two methods:

Using a conda env, and latest versions published in pytorch site (https://pytorch.org/get-started/locally):

conda create -n rtx_3060 python=3.6.5
conda activate rtx_3060
conda install pytorch torchvision torchaudio cudatoolkit=11.1 -c pytorch -c nvidia

apt-get update
apt-get -y install wget
wget -qO- https://get.docker.com/ | sh

sudo apt-get update
sudo apt-get install docker.io

docker version

docker ps -a

###### local settings

git remote add dokku [email protected]:my_api

###### python django rest framework

# apps
dokku apps:create my_api

docker run -it -p 3000:3000 -v $(pwd):/home/ubuntu/code ubuntu:18.04 bash

# dependencies
sudo apt-get update
sudo apt-get install sudo curl wget htop vim git
curl -sL https://deb.nodesource.com/setup_12.x | sudo -E bash -
curl -sS https://dl.yarnpkg.com/debian/pubkey.gpg | sudo apt-key add -
echo "deb https://dl.yarnpkg.com/debian/ stable main" | sudo tee /etc/apt/sources.list.d/yarn.list

mole > https://davrodpin.github.io/mole/

Install local:

bash <(curl -fsSL https://raw.githubusercontent.com/davrodpin/mole/master/tools/install.sh)

# or specific version
wget -c https://raw.githubusercontent.com/p1nox/mole/install_spec_version/tools/install.sh -O mole.sh
bash mole.sh v0.5.0 && rm -f mole.sh

	# version 11.3.0-465.19.01
	wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/cuda-ubuntu2004.pin
	sudo mv cuda-ubuntu2004.pin /etc/apt/preferences.d/cuda-repository-pin-600
	wget https://developer.download.nvidia.com/compute/cuda/11.3.0/local_installers/cuda-repo-ubuntu2004-11-3-local_11.3.0-465.19.01-1_amd64.deb
	sudo dpkg -i cuda-repo-ubuntu2004-11-3-local_11.3.0-465.19.01-1_amd64.deb
	sudo apt-key add /var/cuda-repo-ubuntu2004-11-3-local/7fa2af80.pub
	sudo apt-get update
	sudo apt-get -y install cuda

	<?xml version="1.0" encoding="UTF-8"?>
	<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
	<plist version="1.0">
	<dict>
	<key>Ansi 0 Color</key>
	<dict>
	<key>Alpha Component</key>
	<real>1</real>
	<key>Blue Component</key>
	<real>0.0</real>

	#!/usr/bin/env bash

	pm2 stop web_server

	certbot renew --standalone --preferred-challenges http

	pm2 start web_server