vessel-browser — security grade SAFE, quality 73/100

Security audit verdict: SAFE · quality 73/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by unmodeled-tyler · MCP Server · ★ 131

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is vessel-browser safe to install? View the security audit →

About vessel-browser

Vessel: Your Agent's Browser Open source chromium-based browser for persistent web agents. Linux is the most mature install target today, and macOS release packaging is available from source. Vessel gives external agent harnesses a real browser with durable state, MCP control, and a human-visible supervisory UI. It is built for long-running workflows where the agent drives and the human audits, intervenes, and redirects when needed. Built for agent harnesses such as Hermes Agent, OpenClaw, and other MCP clients Keeps browser state alive with named sessions, pinned tabs, editable/exportable bookmarks, annotated checkpoints, action undo, and structured page visi

agentsai-agentsai-browserai-browser-automationai-mcp-browserai-web-browserautonomous-agentsbyokclaude-mcpcodex-mcp

Quick Facts

Stars131
Forks13
LanguageTypeScript
CategoryMCP Server
LicenseMIT
Quality Score72.5319199412635/100
Open Issues8
Last Updated2026-09-15
Created2026-03-07
Platformsbrowser, claude-code, codex, mcp, node
Est. Tokens~21k

vessel-browser alternative? Top 6 similar tools

Looking for a vessel-browser alternative? If you're comparing vessel-browser with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • dreamgraph by mmethodz · ⭐ 114

    DreamGraph is a graph-governed conceptual development environment (CDE) that turns plans, architecture decisio

  • Dida-Hotel-MCP-Global by DIDA-AI · ⭐ 81

    Official DIDA Hotel Booking MCP Server. 14-year travel tech data stack, 2M+ hotels at wholesale rates, 40+ LLM

  • Dida-RollingGo-Hotel-MCP-Global by DIDA-AI · ⭐ 81

    Official DIDA Hotel Booking MCP Server. 14-year travel tech data stack, 2M+ hotels at wholesale rates, 40+ LLM

  • daymon by daymonio · ⭐ 365

    Daymon puts your favorite AI to work 24/7. It schedules, remembers, and orchestrates your own virtual team. Fr

  • openbrowser-ai by billy-enrizky · ⭐ 244

    OpenBrowser is a framework for intelligent browser automation. It combines direct CDP communication with a Cod

  • google-analytics-mcp by surendranb · ⭐ 242

    Google Analytics 4 data to AI agents, agentic workflows, and MCP clients. Give agents analysis-ready access to

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is vessel-browser?

vessel-browser is Built from the ground-up for agents, Vessel Browser is an open source AI browser for Linux/Mac/Windows that provides a durable state, MCP control, and BYOK with full autonomous browsing. Use with Herm. It is categorized as a MCP Server with 131 GitHub stars.

What programming language is vessel-browser written in?

vessel-browser is primarily written in TypeScript. It covers topics such as agents, ai-agents, ai-browser.

How do I install or use vessel-browser?

You can find installation instructions and usage details in the vessel-browser GitHub repository at github.com/unmodeled-tyler/vessel-browser. The project has 131 stars and 13 forks, indicating an active community.

What license does vessel-browser use?

vessel-browser is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to vessel-browser?

The top alternatives to vessel-browser on Agent Skills Hub include dreamgraph, Dida-Hotel-MCP-Global, Dida-RollingGo-Hotel-MCP-Global. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools