by iLearn-Lab · MCP Server · ★ 60
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
git clone https://github.com/HITSZ-DS/EvoHarness.git
Taken from the project's README on GitHub.
None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 60 |
| Forks | 6 |
| Language | Python |
| Category | MCP Server |
| Quality Score | 62/100 |
| Open Issues | 1 |
| Last Updated | 2026-06-29 |
| Created | 2026-04-05 |
| Platforms | claude-code, mcp, python |
| Est. Tokens | ~17k |
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.
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 first self-evolving AI agent. Rewrites its own source code in real-time. 6 AST mutation strategies. Absorb
An agent runtime for Python. Give your agent real work. Keep control: every action checked before it runs, eve
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:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: