DashClaw — security grade SAFE, quality 63/100

Security audit verdict: SAFE · quality 63/100

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 ucsandman · MCP Server · ★ 306

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

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

About DashClaw

DashClaw Govern AI agents before they act. DashClaw is the governance layer for AI agents that touch real systems. It sits between agents and the world, evaluates policy on every risky action, routes human approval where it is required, records verifiable evidence, and tracks terminal outcomes so a retried agent never silently double-executes. Plugs into the agents you already run: Claude Code, Codex, Hermes Agent, OpenClaw, Claude Desktop, and Claude Managed Agents. Framework integrations for LangChain, CrewAI, AutoGen, LangGraph, and OpenAI Agents SDK. Any other runtime over MCP, the Node/Python SDK, or direct REST. <img src="https://img.shields.io/b

agent-frameworkagent-governanceagent-runtimeai-agentsai-governanceai-infrastructureai-opsautogenclaude-codecrew-ai

Quick Facts

Stars306
Forks52
LanguageTypeScript
CategoryMCP Server
LicenseMIT
Quality Score63.3612813500721/100
Open Issues12
Last Updated2026-09-19
Created2026-02-08
Platformsclaude-code, mcp, node
Est. Tokens~20k

DashClaw alternative? Top 6 similar tools

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

  • Network-AI by Jovancoding · ⭐ 76

    Traffic light for AI Agents and TypeScript/Node multi-agent orchestrator with shared state, guardrails, and ad

  • swarmclaw by swarmclawai · ⭐ 636

    Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory,

  • forge-orchestrator by nxtg-ai · ⭐ 135

    Forge Orchestrator: Multi-AI task orchestration. File locking, knowledge capture, drift detection. Rust.

  • template-repo by AndrewAltimit · ⭐ 131

    Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interp

  • deterministic-agent-control-protocol by elliot35 · ⭐ 88

    Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTT

  • claude-emporium by Vvkmnn · ⭐ 82

    🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is DashClaw?

DashClaw is Remote approvals, policy checks, and execution evidence for unattended AI agents.. It is categorized as a MCP Server with 306 GitHub stars.

What programming language is DashClaw written in?

DashClaw is primarily written in TypeScript. It covers topics such as agent-framework, agent-governance, agent-runtime.

How do I install or use DashClaw?

You can find installation instructions and usage details in the DashClaw GitHub repository at github.com/ucsandman/DashClaw. The project has 306 stars and 52 forks, indicating an active community.

What license does DashClaw use?

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

What are the best alternatives to DashClaw?

The top alternatives to DashClaw on Agent Skills Hub include Network-AI, swarmclaw, forge-orchestrator. 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