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 iLearn-Lab · MCP Server · ★ 56
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is EvoHarness safe to install? View the security audit →
English | ZH-CN EvoHarness delivers terminal-native agent infrastructure: tools, commands, skills, agents, plugins, MCP, memory, approvals, and controlled self-evolution. Build with the project: shape an open, visible, and research-grade harness for coding workflows. <img src="https://img.shields.
| Stars | 56 |
| Forks | 5 |
| Language | Python |
| Category | MCP Server |
| Quality Score | 61.8405821897689/100 |
| Open Issues | 1 |
| Last Updated | 2026-06-29 |
| Created | 2026-04-05 |
| Platforms | claude-code, mcp, python |
| Est. Tokens | ~17k |
These tools work well together with EvoHarness for enhanced workflows:
Looking for a EvoHarness alternative? If you're comparing EvoHarness 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.
The governed runtime for Python agents you can let act: policy on every action, durable runs, sandboxes, budge
MUE-X - self-evolving AI agent. Standalone CLI works anywhere. No Claude Code needed. Gemini & Copilot adapter
Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-f
A ReAct-Based Highly Robust Autonomous Agent (Harness) Framework.
Server-enforced workflow discipline for AI agents. An MCP server providing persistent work items, dependency g
The harness layer for Claude Code — a reference implementation of harness engineering with hook-enforced dual
Explore other popular mcp server tools:
EvoHarness is EvoHarness delivers terminal-native agent infrastructure: tools, commands, skills, agents, plugins, MCP, memory, approvals, and controlled self-evolution. It is categorized as a MCP Server with 56 GitHub stars.
EvoHarness is primarily written in Python. It covers topics such as claude-code, evo, evolution.
You can find installation instructions and usage details in the EvoHarness GitHub repository at github.com/iLearn-Lab/EvoHarness. The project has 56 stars and 5 forks, indicating an active community.
The top alternatives to EvoHarness on Agent Skills Hub include omnicoreagent, mue-x, maestro. 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: