opentabs
Browser automation clicks buttons. OpenTabs calls APIs.
No outside reports on file
OpenTabs gives an AI tool real control over your authenticated browser sessions and can read everything on web pages; only use it for trustworthy websites and monitor what data is being accessed and sent.
Based on public adoption and transparency signals as of Oct 23, 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 sourceGitHub (opentabs-dev/opentabs)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
No npm or PyPI package is listed. Install from source: github.com/opentabs-dev/opentabs ↗
About Opentabs
OpenTabs is an MCP server that automates web browser interactions by clicking buttons and filling forms, while also calling APIs on your behalf. It lets AI assistants control a browser to complete tasks on websites that don't have direct API access.
Who it’s for
Developers and teams who want Claude or other AI tools to interact with web applications that require clicking, scrolling, or form submission. Useful for testing, automation, or integrating websites into AI workflows.
Alternatives
- Playwright or Puppeteer: Low-level browser automation libraries; more control but require writing custom code.
- Selenium: Widely-used open-source tool for browser automation; mature and well-maintained.
- Anthropic's built-in browsing: Claude's native web search and reading features for simpler information retrieval tasks.
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README at https://github.com/opentabs-dev/opentabs (opens external site) for installation and Claude Desktop configuration instructions. The setup typically involves cloning the repository and adding an mcpServers entry to your Claude Desktop config.
Why this grade
Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 1k
- Listing last refreshed
- 2026-10-29
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Security reports
No reports found for this package in our research (last checked 2026-10-29).
Risks to watch for
- Browser session access: The tool controls a real browser with all your cookies, login sessions, and authentication tokens; any malicious input could use these to access your accounts.
- Unvetted website content: Websites can hide deceptive buttons, fake forms, or JavaScript that tricks the automation into clicking the wrong thing or entering sensitive data in the wrong place.
- Data leakage through responses: Web pages may include personal information, API keys, or confidential data in HTML that gets read and returned to the AI or stored in logs.
- No input validation guarantee: If the tool doesn't carefully check what it's automating, attackers could craft prompts that make it exfiltrate data or perform unwanted actions.
- Supply chain risk: Low weekly npm downloads and development activity suggest this tool may not receive regular security updates or maintenance.
How to lower the risk
Least-privilege permissions
- Run the browser in a separate user account or container with no access to sensitive files.
- Use separate browser profiles for automation; never mix personal accounts with automated tasks.
Network isolation
- Restrict the browser to only connect to domains you explicitly need automated.
- Consider running the tool on an isolated VM or network segment if handling sensitive operations.
Monitoring
- Log all URLs visited, buttons clicked, and form data submitted by the automation.
- Review browser history and network requests after each automated session.
Red flags to watch for
- Prompts asking the tool to visit unfamiliar or suspicious websites without clear purpose.
- Requests to fill in API keys, passwords, or personal data into web forms.
- Unexpected or large amounts of data being read from web pages and returned.
Questions
How do I install Opentabs?
Opentabs does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/opentabs-dev/opentabs.
Are there security reports about Opentabs?
No reports found for this package in our research (last checked 2026-10-29). Opentabs currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include browser session access, unvetted website content, data leakage through responses.
Is Opentabs actively maintained?
Opentabs has 1k GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/opentabs-dev/opentabs before pinning it in production.
What are alternatives to Opentabs?
Notable alternatives to Opentabs include Playwright or Puppeteer (Low-level browser automation libraries), Selenium (Widely-used open-source tool for browser automation), Anthropic's built-in browsing (Claude's native web search and reading features for simpler information retrieval tasks). You can also compare Opentabs side by side with other MCP servers in the Related tools section on this page.
README badge and team notes
Maintain or use Opentabs? 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/opentabs-dev-opentabs)HTML embed:
<a href="https://agentarmorhq.com/skills/opentabs-dev-opentabs"><img src="https://agentarmorhq.com/api/badge/opentabs-dev-opentabs" alt="AgentArmorHQ Risk Grade for Opentabs" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "opentabs-dev-opentabs"Share with your security lead
Need sign-off to use opentabs? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: opentabs
- **Listing URL:** https://agentarmorhq.com/skills/opentabs-dev-opentabs
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 1k GitHub stars
#### 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:** GitHub (opentabs-dev/opentabs)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/opentabs-dev/opentabs
- **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 23, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- App connector
- Publisher
- opentabs-dev
- Source code
- github.com/opentabs-dev/opentabs
- Est. context load
- ~500 tokens / turn (~3 tool schemas, 0.25% of 200k context)
- Popularity
- 1k GitHub stars
- Last updated
- 2026-10-29
- Last graded
- 2026-10-23
Community
Discussions for Opentabs
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