# opencode-browser-mcp

> opencode-browser-mcp — mirsella-opencode-browser-mcp. Use this tool when you need to automate browser interactions with shared session management, enabling concurrent agents to run without interference. It solves problems of session isolation and cookie management, allowing agents to leverage existing signed-in sessions and extensions. The tool takes input from browser automation scripts and outputs automated browser interactions, ideal for use cases requiring seamless and efficient browser automation.

Canonical page: https://skillsregistry.net/skills/mirsella-opencode-browser-mcp  
JSON: https://api.skillsregistry.net/v1/skills/mirsella-opencode-browser-mcp

## Description

Browser automation for OpenCode using Chrome DevTools and a shared Chromium profile, with per-session tab isolation so concurrent agents don't interfere. Enables browser agents to use existing signed-in sessions with shared cookies and extensions.

## Trust

- **Trust score (0–1):** 0.07
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/dcmstj4cpc)
- **Repository:** <https://github.com/mirsella/opencode-browser-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "mirsella-opencode-browser-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/mirsella-opencode-browser-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/mirsella-opencode-browser-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt
