Deft — security grade SAFE, quality 66/100

Security audit verdict: SAFE · quality 66/100

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 Maneek21 · MCP Server · ★ 234

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

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

About Deft

Deft Where humans and agents work together. Website Contributing Deft is a self-hostable, open-source workspace where people and AI agents share chat, tasks, knowledge, calendar context, approvals, and action history. Capture a team discussion into knowledge, ask Defty to propose a task using that context, review and approve the proposal, and keep the agreed details in the resulting task. Alpha: for technical evaluation and controlled pilots. The walkthrough uses seeded demo data; it is not evidence of a live customer workspace or an active external agent runtime. Watch the full walkthrough — 5:09. Quick start with Docker Use the prebuilt v0.3.0-preview.15 release for evaluation. It targets Linux amd64 and needs Docker Desktop or Docker Engine with Compose v2. An AI provider is optional. No source build, Node.

agent-platformagplai-agentsai-workspacebyoachatclaudedrizzle-ormhonohuman-ai-collaboration

Quick Facts

Stars234
Forks11
LanguageTypeScript
CategoryMCP Server
LicenseAGPL-3.0
Quality Score65.7668051462978/100
Open Issues10
Last Updated2026-10-02
Created2026-05-12
Platformsclaude-code, docker, mcp, node
Est. Tokens~17k

Deft alternative? Top 6 similar tools

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

  • openhermit by HCF-STUDIOS · ⭐ 85

    OpenHermit is the open-source platform for deploying fleets of AI agents as production services — durable stat

  • capka by LyoSU · ⭐ 51

    Capka AI — An open-source, self-hosted sandbox for AI agents. A community-driven alternative to Claude's Cowor

  • mira-OSS by taylorsatula · ⭐ 477

    This is the public release of MIRA OS. Discrete memories decay through momentum loss, tools auto-configure whe

  • weam by weam-ai · ⭐ 220

    Web app for teams of 20+ members. In-built connections to major LLMs via API. Share chats, prompts, and agents

  • easy-mcp by zcaceres · ⭐ 196

    Absurdly easy Model Context Protocol Servers in Typescript

  • meridian by markmdev · ⭐ 185

    Zero-config Claude Code setup with enforced task scaffolding, structured memory, persistent context after comp

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is Deft?

Deft is Self-hostable AGPL workspace where humans and AI agents share chat, tasks, knowledge, approvals, and MCP context.. It is categorized as a MCP Server with 234 GitHub stars.

What programming language is Deft written in?

Deft is primarily written in TypeScript. It covers topics such as agent-platform, agpl, ai-agents.

How do I install or use Deft?

You can find installation instructions and usage details in the Deft GitHub repository at github.com/Maneek21/Deft. The project has 234 stars and 11 forks, indicating an active community.

What license does Deft use?

Deft is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to Deft?

The top alternatives to Deft on Agent Skills Hub include openhermit, capka, mira-OSS. 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