wave-mcp — security grade SAFE, quality 65/100

Security audit verdict: SAFE · quality 65/100

Flagged: sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by Tencent · MCP Server · ★ 199

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

🔒 Is wave-mcp safe to install? View the security audit →

About wave-mcp

wave-mcp:开源、免 License 的 RTL 波形调试 MCP Server English | 简体中文 wave-mcp 是腾讯蓬莱实验室验证团队开源的一款 RTL 波形调试 MCP Server,为 LLM 提供波形调试工具集: 读 FST 波形 + RTL 网表,提供层次探索、信号查询、驱动分析、值/X 态追踪、波形对比与浏览器波形查看器等 34 个 MCP 工具。 MIT 开源,无需任何商用 License,支持任意并发。 FST 直读,VCD / FSDB 自动转 FST:Verilator 、Icarus 直接产 FST 就能读; 手上只有 VCD 或 FSDB 也没关系, 自动转换后再建 session(FSDB 转换不占 Verdi license)。 它不跑仿真器,你用自己的流程跑出波形,把结果交给它即可。 为什么是 wave-mcp 芯片验证占据开发周期 50% 以上的时间,波形调试是其中最高频的动作。而 LLM 时代, 工程师希望让 AI Agent 直接读波形、查信号、追 X 态根因,但市面上的商用调试 MCP 需要昂贵的 License,且并发受限。 wave-mcp 用纯开源技术栈(pylibfst + pyslang)提供完整波形调试能力: 免 License、数据准确、真实芯片项目背书。 生产级验证 在真实生产级芯片项目(几十个模块)上完整验证,并把 OpenTitan、香山纳入测试集: 特性 波形查询:设计层次、实例、信号(位宽/方向/

chip-verificationdebugedafsdbfstllm-toolsmcppyslangrtlvcd

Quick Facts

Stars199
Forks26
LanguagePython
CategoryMCP Server
Quality Score64.8034753779669/100
Open Issues1
Last Updated2026-09-11
Created2026-07-27
Platformsbrowser, mcp, python
Est. Tokens~17k

Compatible Skills

These tools work well together with wave-mcp for enhanced workflows:

  • RTL-ASS — semantic(0.44)+complementary+rare_topics+same_lang+similar_pop+shared_platform (79%)
  • verilog-generator — semantic(0.36)+complementary+rare_topics+same_lang+similar_pop+shared_platform (76%)
  • veriflow-cc — semantic(0.26)+complementary+rare_topics+same_lang+similar_pop+shared_platform (64%)
  • qwed-verification — semantic(0.25)+complementary+same_lang+similar_pop+shared_platform (59%)

wave-mcp alternative? Top 6 similar tools

Looking for a wave-mcp alternative? If you're comparing wave-mcp 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.

  • TraceWeave by gokeshenzhen · ⭐ 112

    Open-source, evidence-driven MCP server for RTL simulation debugging: correlate VCS/Xcelium logs, VCD/FSDB wav

  • mcp-nixos by utensils · ⭐ 823

    MCP-NixOS - Model Context Protocol Server for NixOS resources

  • llm-functions by sigoden · ⭐ 766

    Easily create LLM tools and agents using plain Bash/JavaScript/Python functions.

  • claude-debugs-for-you by jasonjmcghee · ⭐ 513

    Enable any LLM (e.g. Claude) to interactively debug any language for you via MCP and a VS Code Extension

  • azan-mcp by ahmedeltaher · ⭐ 382

    Azan + Prayer Time + MCP + AI Agents + Islamic + Salah + A lightweight MCP library to calculate prayer times a

  • model-context-protocol-resources by cyanheads · ⭐ 292

    Exploring the Model Context Protocol (MCP) through practical guides, clients, and servers I've built while lea

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is wave-mcp?

wave-mcp is Open-source, license-free MCP server for RTL waveform debug: reads FST waveforms (VCD/FSDB auto-convert) plus a SystemVerilog netlist, with 34 tools covering driver analysis, value/X tracing, pass-fai. It is categorized as a MCP Server with 199 GitHub stars.

What programming language is wave-mcp written in?

wave-mcp is primarily written in Python. It covers topics such as chip-verification, debug, eda.

How do I install or use wave-mcp?

You can find installation instructions and usage details in the wave-mcp GitHub repository at github.com/Tencent/wave-mcp. The project has 199 stars and 26 forks, indicating an active community.

What are the best alternatives to wave-mcp?

The top alternatives to wave-mcp on Agent Skills Hub include TraceWeave, mcp-nixos, llm-functions. 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