AI Agents in Container

by katzByte007

292 downloads

Not rated

GitHub

Description

# AI Agents in Container # kasm Desktop ```bash docker run \ --name browser-use \ --shm-size=4096m \ -w /mnt \ -p 8080:6901 \ -e VNC_PW=password \ -id kasmweb/ubuntu-noble-desktop:1.16.1 user: kasm_user password: password ``` ### browser-use -…

About

Details

Author: katzByte007
Downloads: 292
Categories: Search, AI

- Kasm Ubuntu Noble Desktop with VNC access on port 8080
- browser-use and web-ui installed inside the container
- Ollama integration for local LLM models (e.g., deepseek-r1:8b)
- MCP Puppeteer server configured for multiple IDEs/clients
- Support for Google AI Studio API keys
- Setup instructions for both Linux (Docker) and macOS

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name AI Agents in Container

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "ai agents in container": {
            "AI-Driven-MCP-Server-Data-Processing-Platform": {
                "command": "docker",
                "args": [
                    "run",
                    "\\"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "ai agents in container": {
            "AI-Driven-MCP-Server-Data-Processing-Platform": {
                "command": "docker",
                "args": [
                    "run",
                    "\\"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "ai agents in container": {
            "AI-Driven-MCP-Server-Data-Processing-Platform": {
                "command": "docker",
                "args": [
                    "run",
                    "\\"
                ]
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "ai agents in container": {
            "AI-Driven-MCP-Server-Data-Processing-Platform": {
                "command": "docker",
                "args": [
                    "run",
                    "\\"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "ai agents in container": {
            "AI-Driven-MCP-Server-Data-Processing-Platform": {
                "command": "docker",
                "args": [
                    "run",
                    "\\"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "ai agents in container": {
            "AI-Driven-MCP-Server-Data-Processing-Platform": {
                "command": "docker",
                "args": [
                    "run",
                    "\\"
                ]
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "ai agents in container": {
            "AI-Driven-MCP-Server-Data-Processing-Platform": {
                "command": "docker",
                "args": [
                    "run",
                    "\\"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "ai agents in container": {
            "AI-Driven-MCP-Server-Data-Processing-Platform": {
                "command": "docker",
                "args": [
                    "run",
                    "\\"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "ai agents in container": {
            "AI-Driven-MCP-Server-Data-Processing-Platform": {
                "command": "docker",
                "args": [
                    "run",
                    "\\"
                ]
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "ai agents in container": {
            "AI-Driven-MCP-Server-Data-Processing-Platform": {
                "command": "docker",
                "args": [
                    "run",
                    "\\"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "ai agents in container": {
            "AI-Driven-MCP-Server-Data-Processing-Platform": {
                "command": "docker",
                "args": [
                    "run",
                    "\\"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "ai agents in container": {
            "AI-Driven-MCP-Server-Data-Processing-Platform": {
                "command": "docker",
                "args": [
                    "run",
                    "\\"
                ]
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "ai agents in container": {
            "AI-Driven-MCP-Server-Data-Processing-Platform": {
                "command": "docker",
                "args": [
                    "run",
                    "\\"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "ai agents in container": {
            "AI-Driven-MCP-Server-Data-Processing-Platform": {
                "command": "docker",
                "args": [
                    "run",
                    "\\"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "ai agents in container": {
            "AI-Driven-MCP-Server-Data-Processing-Platform": {
                "command": "docker",
                "args": [
                    "run",
                    "\\"
                ]
            }
        }
    }
}

From the repository

Follow the provided Docker commands to launch a Kasm desktop container, then inside it clone and install browser-use and web-ui. For MCP Puppeteer, build the Docker image and paste the given JSON configuration into VS Code Insiders, Claude Desktop, Cursor, or Codium Windsurf.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "ai agents in container": {
            "AI-Driven-MCP-Server-Data-Processing-Platform": {
                "command": "docker",
                "args": [
                    "run",
                    "\\"
                ]
            }
        }
    }
}

McpServers

{
    "AI-Driven-MCP-Server-Data-Processing-Platform": {
        "command": "docker",
        "args": [
            "run",
            "\\"
        ]
    }
}

AI Agents in Container

kasm Desktop

docker run \
  --name browser-use \
  --shm-size=4096m \
  -w /mnt \
  -p 8080:6901 \
  -e VNC_PW=password \
  -id kasmweb/ubuntu-noble-desktop:1.16.1
  
user: kasm_user
password: password

browser-use

- https://github.com/browser-use/browser-use.git

Install latest version of python

docker exec -u root -it browser-use bash visudo kasm-user ALL=(ALL) NOPASSWD: ALL passwd kasm-user passwd root exit

docker exec -it browser-use bash sudo apt update -y sudo apt install -y python3-venv git xvfb python3-full

web-ui

- https://github.com/browser-use/web-ui.git

# Start in Desktop directory
cd /home/kasm-user/Desktop
Remove any existing web-ui directory if it exists
sudo rm -rf web-ui
Clone the repository
git clone https://github.com/browser-use/web-ui.git
cd web-ui
Create and set up virtual environment in your home directory instead
python3 -m venv ~/web-ui-venv
source ~/web-ui-venv/bin/activate
Install UV
curl -LsSf https://github.com/astral-sh/uv/releases/latest/download/uv-installer.sh | sh
source $HOME/.local/bin/env
Verify environment
whoami
uv --version
python3 --version
Install requirements using the virtual environment in home directory
uv pip install -r requirements.txt
Install Playwright dependencies
playwright install-deps 
playwright install
Setup environment file
cp .env.example .env
Run the application with Xvfb
xvfb-run -a --server-args="-screen 0 1280x1024x24" python webui.py --ip 0.0.0.0 --port 7788
Access the application at:
http://localhost:7788
Remove existing venv
deactivate
cd /home/kasm-user/Desktop
sudo rm -rf web-ui

Install OLLAMA

curl -fsSL https://ollama.com/install.sh | sh ollama serve & http://localhost:11434 ollama pull deepseek-r1:8b ollama pull deepseek-r1:8b # I used this for docker ollama run deepseek-r1:8b ollama list ollama stop deepseek-r1:8b

ollama rm deepseek-r1:8b

MAC OS

- Install latest version of python

brew install python3 git clone https://github.com/browser-use/web-ui.git Install UV Package https://docs.astral.sh/uv/getting-started/installation/ cd web-ui python3 -m venv .venv source .venv/bin/activate curl -LsSf https://github.com/astral-sh/uv/releases/latest/download/uv-installer.sh | sh source $HOME/.local/bin/env uv --version python3 --version uv pip install -r requirements.txt playwright install-deps playwright install cp .env.example .env python webui.py --ip 127.0.0.1 --port 7788

http://localhost:7788

Install OLLAMA on MAC OS

https://ollama.com/download/mac ollama pull deepseek-r1:8b # I used this for Mac OS

ollama run deepseek-r1:8b

Vscode Insiders

- https://code.visualstudio.com/insiders/

Google AI Studio (API Key)

- https://aistudio.google.com/apikey

MCP ServerS

- https://github.com/modelcontextprotocol/servers - https://github.com/punkpeye/awesome-mcp-servers?tab=readme-ov-file#file-systems - https://smithery.ai/

- This provides internet access, so you can get latest documentation and update code accordingly

git clone https://github.com/modelcontextprotocol/servers.git
cd servers
docker build -t mcp/puppeteer -f src/puppeteer/Dockerfile .

- vscode Insider Settings

{

    "mcp": {
"inputs": [],

      "servers": {

        "puppeteer": {

          "command": "docker",

          "args": ["run", "-i", "--rm", "--init", "-e", "DOCKER_CONTAINER=true", "mcp/puppeteer"]

        }

      }

    }

    

  }

- Claude Desktop Settings

{

  "mcpServers": {

    "puppeteer": {

      "command": "docker",

      "args": ["run", "-i", "--rm", "--init", "-e", "DOCKER_CONTAINER=true", "mcp/puppeteer"]

    }

  }

}

- Cursor

{

  "mcpServers": {

    "puppeteer": {

      "command": "docker",

      "args": ["run", "-i", "--rm", "--init", "-e", "DOCKER_CONTAINER=true", "mcp/puppeteer"]

    }

  }

}

- Codium Windsurf

{

  "mcpServers": {

    "puppeteer": {

      "command": "docker",

      "args": ["run", "-i", "--rm", "--init", "-e", "DOCKER_CONTAINER=true", "mcp/puppeteer"]

    }

  }

}

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

Description

About

Details

Jump to

Setting up with Highlight

From the repository

Claude Desktop / Cursor

McpServers

AI Agents in Container

kasm Desktop

browser-use

Install latest version of python

web-ui

Remove any existing web-ui directory if it exists

Clone the repository

Create and set up virtual environment in your home directory instead

Install UV

Verify environment

Install requirements using the virtual environment in home directory

Install Playwright dependencies

Setup environment file

Run the application with Xvfb

Access the application at:

http://localhost:7788

Remove existing venv

Install OLLAMA

MAC OS

Install UV Package https://docs.astral.sh/uv/getting-started/installation/

Install OLLAMA on MAC OS

Vscode Insiders

Google AI Studio (API Key)

MCP ServerS

Install

More like this

Brave Search

Context 7

1Panel

🔎 GPT Researcher

Serena

FastMCP v2 🚀