Browser Automation

io.github.mindstone/mcp-server-browser-automation·v0.1.8·Browser Automation

Browser automation MCP server: navigate, fill forms, click, screenshot, and manage tabs

In-path gate · all MCP tools

Using Browser Automation in Claude, Cursor, Gemini CLI, Cline, or Zed?

MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and HOLDs the call when it drifts—before your agent acts. Zero credentials. This is not the package install for this server itself (use Install this server for that).

Install the mcpindex gate (one command)

Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less

curl -fsSL https://mcpindex.ai/install.sh | sh

Auditable install path →Watch it hold a drift →

Trust verdict · v1 advisory · method

REVIEWstatus: PARTIALfresh until 2026-08-04 09:03 UTC

screened 2026-07-05tier: scannedgranularity: description-levelsource: registry

Semantic screen found no manipulation pattern in the description. Conformance probe not yet run.

mcpindex.integrity.descriptionpassINFO

evidence“No malicious instructions found”via static_description

Limits of this verdict

- Semantic screen only - the deterministic conformance probe has not run on this server
- Confidence is reported but not yet calibrated (v1)
- Screen reads the tool description, not the live behavior
- advisory
- registry description only no input schema
- screen model 8b

Semantic screen: an LLM judge reads the tool description for hidden instructions (status PARTIAL). A pass means the description is not lying, not that the tool is safe: a high-capability tool with an honest description still warrants caution. The deterministic conformance probe has not been run on this server yet, so the screen here is semantic-only. Posture: advisory. Confidences are reported but not yet calibrated (calibrated=false at v1). Full verdict history is not shown on this page.

Own this server? Screen its description →

Embed this badge

A live verdict badge for your README or listing. It reflects the current screen, links back here, and updates when the verdict does.

Markdown

[![mcpindex](https://mcpindex.ai/api/v1/badge/io-github-mindstone-mcp-server-browser-automation)](https://mcpindex.ai/server/io-github-mindstone-mcp-server-browser-automation)

HTML

<a href="https://mcpindex.ai/server/io-github-mindstone-mcp-server-browser-automation"><img src="https://mcpindex.ai/api/v1/badge/io-github-mindstone-mcp-server-browser-automation" alt="mcpindex verdict" height="20" /></a>

Environment variables

AGENT_BROWSER_SESSION_NAME

Session name for browser persistence

AGENT_BROWSER_SHOW_WINDOW

Set to 'false' to run the browser headless. Default is visible (true).

BROWSER_AUTOMATION_ALLOW_EVAL

Set to 1 to register the browser_evaluate tool (off by default for security)

MCP quality score · maturity, not trust · methodology

freshness

completeness

installability

documentation

stability

Alternatives in Browser Automation

ai.foura/mcp

Web scraping for AI agents: fetch any page via proxy or full browser, past anti-bot defenses.

ai.openhelm/openhelm

Autonomous cloud agent tasks: real browser + your tools, structured evidence-backed results.

ai.smithery/ImRonAI-mcp-server-browserbase

Automate cloud browsers to navigate websites, interact with elements, and extract structured data.…

Install this server

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "mcp-server-browser-automation": {
      "command": "npx",
      "args": [
        "-y",
        "@mindstone/mcp-server-browser-automation"
      ],
      "env": {
        "AGENT_BROWSER_SESSION_NAME": "mcp",
        "AGENT_BROWSER_SHOW_WINDOW": "true",
        "BROWSER_AUTOMATION_ALLOW_EVAL": "<browser_automation_allow_eval>"
      }
    }
  }
}

Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "mcp-server-browser-automation": {
      "command": "npx",
      "args": [
        "-y",
        "@mindstone/mcp-server-browser-automation"
      ],
      "env": {
        "AGENT_BROWSER_SESSION_NAME": "mcp",
        "AGENT_BROWSER_SHOW_WINDOW": "true",
        "BROWSER_AUTOMATION_ALLOW_EVAL": "<browser_automation_allow_eval>"
      }
    }
  }
}

Cline (cline_mcp_settings.json)

npx -y @mindstone/mcp-server-browser-automation

Claude Code (claude mcp add)

claude mcp add --scope user mcp-server-browser-automation -- npx -y @mindstone/mcp-server-browser-automation

Gemini CLI (gemini mcp add)

gemini mcp add -s user mcp-server-browser-automation npx -y @mindstone/mcp-server-browser-automation

Verdict API

curl -s mcpindex.ai/api/v1/trust/server/io-github-mindstone-mcp-server-browser-automation

Free-tier verdict as JSON: decision + dimensions + severity. Call it from your agent before it invokes a tool it just discovered.

Details

version: v0.1.8
category: Browser Automation
verdict expires: 2026-08-04
quality: 85 / 100
operator: mindstone

Provenance

Verdict history is anchored to Bitcoin via OpenTimestamps. The anchor proof is public and any skeptic can recompute it offline.

Links

Repository →