An interactive Streamlit dashboard allowing users to pilot a headless browser instance using natural language instructions. The backend hooks into the Model Context Protocol (MCP) and Playwright.
Developed by Coder Coder. For more projects, interviews, and OA preparation, please visit CodinzHub.
Navigate to this agent's folder:
cd mcp_integrations_agents/browser_mcp_agent
Install python packages:
pip install -r requirements.txt
Confirm Node.js is present:
node --version
npm --version
Configure your OpenAI access token: Set the environment variable:
export OPENAI_API_KEY=your-openai-api-key
Or set it within mcp_agent.secrets.yaml (copy it from mcp_agent.secrets.yaml.example if needed).
This agent supports local LLM execution using Ollama:
Launch Ollama and pull a tool-compatible model:
ollama pull llama3.2
ollama serve
Modify mcp_agent.config.yaml to point to Ollama's endpoint:
openai:
base_url: "http://localhost:11434/v1"
default_model: "llama3.2"
Add a placeholder token in mcp_agent.secrets.yaml:
openai:
api_key: "ollama"
Run the Streamlit console:
streamlit run main.py
Open the page in your browser, specify your instructions, and click Execute Command.
Go to codinzhub.comScroll down to view more contentClick on the search inputClick on the login buttonSummarize the main content of this pageTake a screenshot of the main headerThis assistant runs on:
Developed by Coder Coder. For more projects, interviews, and OA preparation, please visit CodinzHub.
Download the complete source code for this project. Extract the ZIP file and follow the instructions in the README to run it locally.
Download Project (ZIP)