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 evilsocket · MCP Server · ★ 1.3k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is nerve safe to install? View the security audit →
The Simple Agent Development Kit Join the project community on our server! <a
| Stars | 1,316 |
| Forks | 115 |
| Language | Python |
| Category | MCP Server |
| Quality Score | 59.2963678552397/100 |
| Open Issues | 4 |
| Last Updated | 2025-08-23 |
| Created | 2024-06-07 |
| Platforms | cli, mcp, python |
| Est. Tokens | ~362k |
These tools work well together with nerve for enhanced workflows:
Looking for a nerve alternative? If you're comparing nerve 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.
Klavis AI: MCP integration platforms that let AI agents use tools reliably at any scale
The python library for research and development in NLP, multimodal LLMs, Agents, ML, Knowledge Graphs, and mor
Flow-Like: Strongly Typed Enterprise Scale Workflows. Built for scalability, speed, seamless AI integration an
Ultimate Context Engineering Infrastructure, starting from MCPs and Integrations
An introduction to the world of AI Agents
A model-driven approach to building AI agents in just a few lines of code.
Explore other popular mcp server tools:
nerve is The Simple Agent Development Kit.. It is categorized as a MCP Server with 1.3k GitHub stars.
nerve is primarily written in Python. It covers topics such as adk, agent-based-modeling, agent-development-kit.
You can find installation instructions and usage details in the nerve GitHub repository at github.com/evilsocket/nerve. The project has 1.3k stars and 115 forks, indicating an active community.
The top alternatives to nerve on Agent Skills Hub include klavis, npcpy, flow-like. 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: