Browser UseCAUTION
None
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
MCP server that gives AI assistants the power to control a web browser.
[](LICENSE)
Table of Contents
- What is this?
- Installation
- Web UI
- Web Dashboard
- Configuration
- CLI Reference
- MCP Tools
- Deep Research
- Observability
- Skills System
- REST API Reference
- Architecture
- License
What is this?
This wraps browser-use as an MCP server, letting Claude (or any MCP client) automate a real browser—navigate pages, fill forms, click buttons, extract data, and more.
Why HTTP instead of stdio?
Browser automation tasks take 30-120+ seconds. The standard MCP stdio transport has timeout issues with long-running operations—connections drop mid-task. HTTP transport solves this by running as a persistent daemon that handles requests reliably regardless of duration.
Installation
Claude Code Plugin (Recommended)
Install as a Claude Code plugin for automatic setup:
# Install the plugin /plugin install browser-use/mcp-browser-use
The plugin automatically:
- Installs Playwright browsers on first run
- Starts the HTTP daemon when Claude Code starts
- Registers the MCP server with Claude
Set your API key (the browser agent needs an LLM to decide actions):
# Set API key (environment variable - recommended) export GEMINI_API_KEY=your-key-here # Or use config file mcp-server-browser-use config set -k llm.api_key -v your-key-here
That's it! Claude can now use browser automation tools.
Manual Installation
For other MCP clients or standalone use:
# Clone and install git clone https://github.com/Saik0s/mcp-browser-use.git cd mcp-serv
76b370da3389OBSERVED · 2026-09-26Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp_server_browser_use --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} --env GEMINI_API_KEY=${GEMINI_API_KEY} --env OPENAI_API_KEY=${OPENAI_API_KEY} -- uvx mcp_server_browser_use{
"mcpServers": {
"mcp_server_browser_use": {
"command": "uvx",
"args": [
"mcp_server_browser_use"
],
"env": {
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"GEMINI_API_KEY": "${GEMINI_API_KEY}",
"OPENAI_API_KEY": "${OPENAI_API_KEY}"
}
}
}
}Exposed tools (9)
6 read · 2 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
health_check | read | |
run_browser_agent | write | |
run_deep_research | write | |
skill_delete | destructive | |
skill_get | read | |
skill_list | read | |
task_cancel | read | |
task_get | read | |
task_list | read |
Trust audit
CAUTIONgrade B · trust 88/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (4 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (11)
return f"http://127.0.0.1:{port}"skill_delete
.pre-commit-config.yaml
CLAUDE.md
- Default URL: http://127.0.0.1:8383/mcp
("http://127.0.0.1/", True),("http://192.168.1.1/", True),("http://10.0.0.1/", True),body = base64.b64decode(body).decode("utf-8", errors="replace")5. **Configuration Timing**: Load environment variables before importing server module
curl -sSL https://raw.githubusercontent.com/steveyegge/beads/main/scripts/install.sh | bash
Gates applied: no_behavioural_pass.
76b370da3389full audit observations/trust-audit/mcp-server/saik0s__browser-use.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-09-26 | 76b370da3389 | CAUTION | B | 88 | first audit |
Questions
What is the Browser Use MCP server?
None
What tools does Browser Use expose?
9 in total: 6 read-only, 2 that write, and 1 that can delete or overwrite (skill_delete). Every one is listed on this page with its risk.
Is Browser Use safe to connect to an agent?
With care. The audit graded it B (88/100) and found 11 things worth knowing before you trust this server, listed below with the exact line each was found on. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Browser Use need?
It reads ANTHROPIC_API_KEY, GEMINI_API_KEY and OPENAI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Browser Use run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as mcp_server_browser_use.
How current is this page?
The grade is for one exact copy of the source (76b370da3389), read on 2026-09-26. The repository is watched and re-audited when it changes.