mcp-pointer — security grade SAFE, quality 69/100

Security audit verdict: SAFE · quality 69/100

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 etsd-tech · MCP Server · ★ 591

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

🔒 Is mcp-pointer safe to install? View the security audit →

About mcp-pointer

👆 MCP Pointer Point to browser DOM elements for agentic coding tools via MCP! MCP Pointer is a local tool combining an MCP Server with a Chrome Extension: 🖥️ MCP Server (Node.js package) - Bridges between the browser and AI tools via the Model Context Protocol 🌐 Chrome Extension - Captures DOM element selections in the browser using The extension lets you visually select DOM elements in the browser, and the MCP server makes this textual context available to

agentic-codingbrowserclaude-codecursordomdom-elementmcpmcp-serverpointingstdio

Quick Facts

Stars591
Forks58
LanguageTypeScript
CategoryMCP Server
LicenseMIT
Quality Score68.6952139593045/100
Open Issues7
Last Updated2025-11-12
Created2025-09-01
Platformsbrowser, claude-code, mcp, node
Est. Tokens~32k

Compatible Skills

These tools work well together with mcp-pointer for enhanced workflows:

  • agentic — semantic(0.24)+complementary+rare_topics+same_lang+similar_pop+shared_platform (58%)
  • Mysti — semantic(0.20)+complementary+rare_topics+same_lang+similar_pop+shared_platform (56%)
  • tdd-guard — semantic(0.18)+complementary+rare_topics+same_lang+similar_pop+shared_platform (56%)
  • Frame — semantic(0.35)+complementary+rare_topics+similar_pop+shared_platform (52%)
  • jeffreysprompts.com — semantic(0.17)+complementary+same_lang+similar_pop+shared_platform (51%)

mcp-pointer alternative? Top 6 similar tools

Looking for a mcp-pointer alternative? If you're comparing mcp-pointer 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.

  • vibetest-use by browser-use · ⭐ 821

    Vibetest MCP - automated QA testing using Browser-Use agents

  • browser-use-mcp-server by kontext-dev · ⭐ 811

    Browse the web, directly from Cursor etc.

  • Claude-Skills by borghei · ⭐ 805

    372 AI skills, 76 expert agents, and 867 stdlib Python tools for every team: engineering, PM, marketing, C-lev

  • memorix by AVIDS2 · ⭐ 797

    Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Wi

  • claude-talk-to-figma-mcp by arinspunk · ⭐ 662

    A Model Context Protocol (MCP) that allows Claude Desktop and other AI tools (Claude Code, Cursor, Antigravity

  • Overture by SixHq · ⭐ 641

    Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is mcp-pointer?

mcp-pointer is MCP tool: let you point at DOM elements for your favorite agentic coding tool. Let AI see what you see.. It is categorized as a MCP Server with 591 GitHub stars.

What programming language is mcp-pointer written in?

mcp-pointer is primarily written in TypeScript. It covers topics such as agentic-coding, browser, claude-code.

How do I install or use mcp-pointer?

You can find installation instructions and usage details in the mcp-pointer GitHub repository at github.com/etsd-tech/mcp-pointer. The project has 591 stars and 58 forks, indicating an active community.

What license does mcp-pointer use?

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

What are the best alternatives to mcp-pointer?

The top alternatives to mcp-pointer on Agent Skills Hub include vibetest-use, browser-use-mcp-server, Claude-Skills. 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