Flagged: opens a tunnel service. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by truffle-ai · MCP Server · ★ 651
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is dexto safe to install? View the security audit →
Deutsch | English | Español | français | 日本語 | 한국어 | Português | Русский | 中文 An open agent harness
| Stars | 651 |
| Forks | 80 |
| Language | TypeScript |
| Category | MCP Server |
| Quality Score | 69.333323154961/100 |
| Open Issues | 71 |
| Last Updated | 2026-09-22 |
| Created | 2025-03-24 |
| Platforms | cli, mcp, node |
| Est. Tokens | ~19k |
Looking for a dexto alternative? If you're comparing dexto 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.
MCP server for semantic code research and context generation on real-time using LLM patterns | Search naturall
Easily create LLM tools and agents using plain Bash/JavaScript/Python functions.
AI agent microservice
superglue (YC W25) builds integrations and tools from natural language. Get production-grade tools for long ta
Create AI Agents in a No-Code Visual Builder or TypeScript SDK with full 2-way sync. For shipping AI assistant
A list of open-source AI projects you can use to generate income easily.
Explore other popular mcp server tools:
dexto is Agent harness and tookit for building AI agents and agentic applications. CLI and SDKs included. It is categorized as a MCP Server with 651 GitHub stars.
dexto is primarily written in TypeScript. It covers topics such as ai, ai-agent, ai-agents.
You can find installation instructions and usage details in the dexto GitHub repository at github.com/truffle-ai/dexto. The project has 651 stars and 80 forks, indicating an active community.
The top alternatives to dexto on Agent Skills Hub include octocode-mcp, llm-functions, core. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: