clawdcursor — security grade SAFE, quality 64/100

Security audit verdict: SAFE · quality 64/100

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 AmrDab · MCP Server · ★ 403

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

🔒 Is clawdcursor safe to install? View the security audit →

About clawdcursor

Clawd Cursor The local MCP server that gives any agent safe desktop control. Any model. Any app. One MCP entry. Local-only. Quickstart</a

ai-agentai-toolsanthropicautomationclaudecomputer-usecross-platformcursordesktopdesktop-automation

Quick Facts

Stars403
Forks59
LanguageTypeScript
CategoryMCP Server
LicenseMIT
Quality Score63.8952630746041/100
Open Issues9
Last Updated2026-10-03
Created2026-02-19
Platformsclaude-code, mcp, node
Est. Tokens~22k

Compatible Skills

These tools work well together with clawdcursor for enhanced workflows:

  • open-computer-use — semantic(0.18)+complementary+rare_topics+same_lang+similar_pop+shared_platform (61%)
  • agent-skills — semantic(0.21)+complementary+rare_topics+same_lang+similar_pop+shared_platform (57%)
  • os-ai-computer-use — semantic(0.36)+complementary+rare_topics+similar_pop+shared_platform (57%)
  • gemini-desktop — semantic(0.23)+complementary+same_lang+similar_pop+shared_platform (53%)
  • easyclaw — semantic(0.20)+complementary+same_lang+similar_pop+shared_platform (52%)

clawdcursor alternative? Top 6 similar tools

Looking for a clawdcursor alternative? If you're comparing clawdcursor 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.

  • toolhive-studio by stacklok · ⭐ 169

    ToolHive is an application that allows you to install, manage and run MCP servers and connect them to AI agent

  • native-devtools-mcp by sh3ll3x3c · ⭐ 125

    MCP server for computer use & browser automation - screenshot, OCR, click, type, find_text, Chrome/Electron C

  • Overture by SixHq · ⭐ 641

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

  • flutter-skill by ai-dashboad · ⭐ 362

    AI-powered E2E testing for 10 platforms. 253 MCP tools. Zero config. Works with Claude, Cursor, Windsurf, Copi

  • mcp-fusion by vinkius-labs · ⭐ 204

    MCP Fusion - The framework for AI-native MCP servers.

  • os-ai-computer-use by 777genius · ⭐ 181

    AI controls your OS. OS AI Computer Use, OS and API agnostic. For now on OpenAI and Anthropic API. Desktop app

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is clawdcursor?

clawdcursor is clawdcursor compiles whatever's on screen into one UI map — accessibility tree and OCR fused into stable, addressable elements, with a screenshot only when needed — then drives apps through reusable s. It is categorized as a MCP Server with 403 GitHub stars.

What programming language is clawdcursor written in?

clawdcursor is primarily written in TypeScript. It covers topics such as ai-agent, ai-tools, anthropic.

How do I install or use clawdcursor?

You can find installation instructions and usage details in the clawdcursor GitHub repository at github.com/AmrDab/clawdcursor. The project has 403 stars and 59 forks, indicating an active community.

What license does clawdcursor use?

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

What are the best alternatives to clawdcursor?

The top alternatives to clawdcursor on Agent Skills Hub include toolhive-studio, native-devtools-mcp, Overture. 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