agent-browser
A real Chromium browser agents pay for per action in USDC via x402 — hosted MCP, free local stdio.
No outside reports on file
agent-browser fetches arbitrary web URLs and links no public GitHub repository; restrict its folder reach, network access, and credentials before installing.
Based on public adoption and transparency signals as of Oct 27, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionNo shell command runner notedLOW
- Network reachFetches arbitrary web URLsREVIEW
- CredentialsNo API token requiredLOW
- Package sourceSource repository onlyPUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
We hold no install steps for this listing. Follow the project’s own instructions.
About Agent Browser
Agent Browser is an MCP server focused on Web & browsing: A real Chromium browser agents pay for per action in USDC via x402 — hosted MCP, free local stdio.
No standalone npm or PyPI registry package is linked on file; review the project links before installing. Based on its public metadata, its operational scope includes: fetches arbitrary web urls.
Setup
We hold no install steps for Agent Browser. Follow the project’s own instructions.
Why this grade
Signal-based grade (0/7 points): no public source code found. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- Listing last refreshed
- 2026-10-27
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Security reports
We could not reach our research just now, so this list may be incomplete. Try again later.
Risks to watch for
- Untrusted web content & prompt injection: Fetches arbitrary web pages or remote endpoints where hidden instructions could manipulate agent behavior. Restrict outbound domains and review tool outputs.
- Unlinked source code repository: No public GitHub repository or registry package is linked on file. Verify the publisher identity and inspect the code before running it locally.
How to lower the risk
Least-privilege permissions
- Give it access only to the specific folders, accounts or projects it needs, never your whole drive or admin account.
- Use a separate, limited API key or login just for this tool so you can switch it off without affecting anything else.
Network isolation
- Run it on a work computer or sandbox account, not one holding personal or company-sensitive data.
- If your IT team can, limit which websites and services it is allowed to contact.
Monitoring
- Check its activity history or logs weekly at first, and look at what it changed or sent.
- Turn on alerts for new logins or unusual usage on any account it connects to.
Red flags to watch for
- It asks for more access than its job requires, or prompts you to paste passwords.
- It suddenly updates with new owners, or starts contacting unfamiliar websites.
Questions
How do I install Agent Browser?
No standalone npm or PyPI package is listed for Agent Browser. Use the project links in the Key facts section on this page for installation steps.
Are there security reports about Agent Browser?
No reports found for this package in our research. Agent Browser currently holds Grade F (Many risk signals) based on public adoption and transparency signals. Review the permissions and source repository before granting access to local files, shell commands, or API keys.
Is Agent Browser actively maintained?
We do not have star or download counts on file for Agent Browser yet (listing refreshed 2026-10-27). Check the commit history and open issues before relying on it.
What are alternatives to Agent Browser?
You can compare Agent Browser side by side with other Browser MCP servers in the Related tools section on this page, or use the Compare tool on AgentArmorHQ.
README badge and team notes
Maintain or use Agent Browser? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/agent-browser)HTML embed:
<a href="https://agentarmorhq.com/skills/agent-browser"><img src="https://agentarmorhq.com/api/badge/agent-browser" alt="AgentArmorHQ Risk Grade for Agent Browser" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "agent-browser"Share with your security lead
Need sign-off to use agent-browser? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: agent-browser
- **Listing URL:** https://agentarmorhq.com/skills/agent-browser
- **Type:** App connector
- **Risk Grade:** Grade F (Many risk signals)
- **Outside Security Advisories on File:** 0
#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Fetches arbitrary web URLs
- **Credentials:** No API token required
- **Package source:** Source repository only
#### Recommended Hardened Setup
- Follow repository setup instructions.
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 27, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- App connector
- Est. context load
- ~850 tokens / turn (~5 tool schemas, 0.43% of 200k context)
- Last updated
- 2026-10-27
- Last graded
- 2026-10-27
Community
Discussions for Agent Browser
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude