Hello, I'm Rijul, and I'm building LiveReview — a blast-radius aware AI code review built for your business-critical systems. Star us to help devs discover the project, give it a try, and share your feedback to help improve the product.
We use AI agents for all sorts of tasks. Some agents can even interact with your browser and act as companions while you work.
As someone who uses OpenCode, I wanted to bring that capability into my workflow. I wanted OpenCode to interact with my browser so it could access the relevant browser context while helping me with tasks.
In this article, let's see how to connect your browser to OpenCode using Browser MCP.
1. What You Need
To set this up, you need two components:
- Browser extension: Connects your browser to the MCP server.
- Local MCP server: Allows your AI client to interact with the browser through the Model Context Protocol (MCP).
Let's set them up.
2. Install the Browser Extension
First, visit the following page to install the Browser MCP extension:
After installing the extension, you'll be directed to a page with more information.
This page links to the official Browser MCP documentation, where you can find additional setup instructions and details about how it works:
3. Add the MCP Server to OpenCode
Next, configure OpenCode to use the Browser MCP server.
Open your OpenCode configuration file and add the following configuration:
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"browsermcp": {
"type": "local",
"command": ["npx", "-y", "@browsermcp/mcp@latest"]
}
}
}
This configuration tells OpenCode to start the Browser MCP server locally using npx.
Save the configuration after adding it.
4. Connect and Test the Browser
Once you've configured the MCP server, make sure Browser MCP is connected.
Now, let's test whether it works.
Go to OpenCode and give it a task that requires browser interaction. For example:
Go to the Wikipedia page for "Open-source software" and list the main section headings.
The Browser MCP server allows OpenCode to interact with the browser and navigate to the requested page.
Here's the result returned by the agent.
As you can see, OpenCode can use the browser to complete the task instead of relying only on the information already available in the conversation.
Conclusion
That's how you can connect Browser MCP to OpenCode.
This setup lets you bring browser interaction into your AI-assisted workflow. Instead of working with your AI agent and browser separately, you can give OpenCode tasks that involve navigating web pages and gathering information through the connected browser.
It can be useful when you want your AI coding assistant to work with relevant information from the web alongside your existing workflow.
That's it for this article. See you in the next one!
Your team's attention is limited, and the deluge of AI-generated code is making it harder to keep production reliable and secure without slowing you down.
I'm building LiveReview, a blast-radius aware AI code review built for your business-critical systems.
Instead of presenting every diff with equal emphasis, LiveReview scores each change by blast radius — how far its impact reaches through your call graph — so you can focus attention where it actually matters.
Spend code review effort where business risk is highest — not spread evenly across every diff.
⭐ Star it on GitHub:
HexmosTech
/
LiveReview
Risk-Aware AI Code Review for Business-Critical Systems
LiveReview: Risk-Aware AI Code Review for Business-Critical Systems
LiveReview is an AI code reviewer that scores every hunk of a diff by blast radius: how far a change reaches through your call graph, how much persistent state it touches, and how well-tested it is. A 3-line change to a shared auth check can outrank a 300-line UI tweak. Your team's attention goes to the highest-risk code first, not spread evenly across every diff.
blast-radius-demo.mp4
LiveReview's Blast Radius & Review Priority scoring, live in the diff viewer.
The exact math, not a black box
Visualize blast radius at a glance
Every factor that feeds the score
Here's the goal:
- A 3-line fix in a function used by 40 other files, that also writes to a database, should score high.
- A 300-line UI change in one file, fully covered by tests…
Click below to try LiveReview with your codebase:
Top comments (0)