Prototype · Preview: every server in the official registry, synced every 30 minutes. Sign in with Google to write reviews.Prototype · updated every 30 min
PopNx MCPMCP servers for people who use AI · explained in plain words

Vivado MCP Native

by Arthurzxyversion 0.2.1i★ 0iRuns on your computerRepository ↗
Registry nameio.github.Arthurzxy/vivado-mcp-native

How to install

What it does

Native MCP server for controlling AMD/Xilinx Vivado on Windows and Linux via persistent Tcl.

  • Connects Runs on your computer
  • Account or key No key needed
  • Category Developer tools

Use together with

Skills that teach the AI this kind of work; they work alongside this one

rea

Reverse engineer anything with agents, from app behavior down to native binaries.

by morluto★ 467,2351 skills

Skill · How-to guide

andrej-karpathy-skills

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

by multica-ai★ 234,1251 skills

Skill · How-to guideNo license stated

graphify

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

by Graphify-Labs★ 149,8731 skills

Skill · How-to guide

Why it ranks here

Lists are ordered by a usage score (out of 100) built from these parts

Popularity0/80GitHub stars or weekly downloads: the larger counts 60, the smaller 20
Freshness3/12Full marks for a release or code change within 30 days
Still answering0/8The cloud endpoint answered at the last check
Usage score3/100

Quality: Passed 3/3 basic checks (shown, not used for ordering) · Momentum: No data yet (Used only on the Trending tab)

Install

Pick the AI app you use, then copy the settings.

Let your AI install it with one sentence

Please install Vivado MCP Native. Follow https://mcp.popnx.com/i/arthurzxy-vivado-mcp-native.md, show me the commands and wait for my OK before running them.

Paste it into an AI that can work on your computer (such as Claude Code or Cursor). It reads our steps, shows you the commands and waits for your OK. No key, no sign-up. · See the full text your AI reads

Passed 3/3 checks · Runs on your computer · ✓ Commands checked Nov 14, 2026

First: which AI do you use?

Pick your app and the steps appear below.

Works with Claude, with some setup first

Install Python (uv) on your computer first (one time) · Only the Claude desktop app (Windows or Mac), not the web or phone

Let AI install it

Copy this message into a Claude chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.

Please install the MCP server Vivado MCP Native for Claude on this computer, in this order: 1) Check uv with uv --version. If it is missing, tell me to install it from https://docs.astral.sh/uv/getting-started/installation/; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "mcpServers": { "vivado-native": { "command": "uvx", "args": [ "vivado-mcp-native" ] } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) No key is needed. 5) Do what we agreed, then check that the Vivado MCP Native tools really show up.

This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.

  1. Install uv (if you don’t have it)

    Already installed? Check first · Open Terminal, type this command and press Enter

    uv --version
    • A version number such as uv … = installed, skip this step
    • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
    How to open Terminal

    Mac: press ⌘ + Space, type Terminal, press Enter

    Windows: open Start, type Windows PowerShell, then Open

    Not installed: uv has no click-through installer. Copy the one-line command for your system (macOS or Windows) from uv’s official page into Terminal · no separate Python install needed; uv downloads it when required

    Open the uv download page ↗

    When it’s done, close Terminal, open it again and run the same command. You should see a version number: uv --version

    Install once; it works for everything that needs uv

  2. Open the Claude desktop app’s settings file

    SettingsDeveloperEdit Config

  3. Paste these settings and save the file

    {
      "mcpServers": {
        "vivado-native": {
          "command": "uvx",
          "args": [
            "vivado-mcp-native"
          ]
        }
      }
    }
  4. Quit Claude and open it again

  5. Try it

    Use Vivado MCP Native and tell me what you can do for me, then show me one thing

    ✓ If Claude says it is using Vivado MCP Native or shows a Vivado MCP Native tool in the answer, you are connected

2 optional setting(s) (works without them)

The command above works without these. Add them only if you want to change something, following the maker’s description.

  • VIVADO_PATH Optional path to a Vivado launcher, bin directory, or version directory.
  • VIVADO_MCP_OUTPUT_ENCODING Optional Vivado Tcl console output encoding, such as utf-8 or gbk.

Descriptions are as written by the maker.

Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version

ChatGPT cannot connect Vivado MCP Native yet

Vivado MCP Native runs on your computer, but ChatGPT can only connect servers that run on the web

What you can do instead

A · Use an app that can connect Vivado MCP Native

  • Install Python (uv) on your computer first (one time) · Only the Claude desktop app (Windows or Mac), not the web or phone
  • Install Python (uv) on your computer first (one time)
  • Install Python (uv) on your computer first (one time)
  • Install Python (uv) on your computer first (one time)

B · Others in Developer tools that work with ChatGPT

Picked from the most used in the same category, only ones that connect by address with no key

Works with Claude Code, with some setup first

Install Python (uv) on your computer first (one time)

Let AI install it

Copy this message into a Claude Code chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.

Please install the MCP server Vivado MCP Native for Claude Code on this computer, in this order: 1) Check uv with uv --version. If it is missing, tell me to install it from https://docs.astral.sh/uv/getting-started/installation/; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): claude mcp add --scope user vivado-native -- uvx vivado-mcp-native 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) No key is needed. 5) Do what we agreed, then check that the Vivado MCP Native tools really show up.

This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.

  1. Install uv (if you don’t have it)

    Already installed? Check first · Open Terminal, type this command and press Enter

    uv --version
    • A version number such as uv … = installed, skip this step
    • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
    How to open Terminal

    Mac: press ⌘ + Space, type Terminal, press Enter

    Windows: open Start, type Windows PowerShell, then Open

    Not installed: uv has no click-through installer. Copy the one-line command for your system (macOS or Windows) from uv’s official page into Terminal · no separate Python install needed; uv downloads it when required

    Open the uv download page ↗

    When it’s done, close Terminal, open it again and run the same command. You should see a version number: uv --version

    Install once; it works for everything that needs uv

  2. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: open PowerShell

  3. Paste this command and press Enter

    claude mcp add --scope user vivado-native -- uvx vivado-mcp-native
  4. Type /mcp in Claude Code

    You should see Vivado MCP Native listed as connected

  5. Try it

    Use Vivado MCP Native and tell me what you can do for me, then show me one thing

    ✓ If Claude Code says it is using Vivado MCP Native or shows a Vivado MCP Native tool in the answer, you are connected

2 optional setting(s) (works without them)

The command above works without these. Add them only if you want to change something, following the maker’s description.

  • VIVADO_PATH Optional path to a Vivado launcher, bin directory, or version directory.
  • VIVADO_MCP_OUTPUT_ENCODING Optional Vivado Tcl console output encoding, such as utf-8 or gbk.

Descriptions are as written by the maker.

Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Works with Cursor, with some setup first

Install Python (uv) on your computer first (one time)

Let AI install it

Copy this message into a Cursor chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.

Please install the MCP server Vivado MCP Native for Cursor on this computer, in this order: 1) Check uv with uv --version. If it is missing, tell me to install it from https://docs.astral.sh/uv/getting-started/installation/; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "mcpServers": { "vivado-native": { "command": "uvx", "args": [ "vivado-mcp-native" ] } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) No key is needed. 5) Do what we agreed, then check that the Vivado MCP Native tools really show up.

This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.

  1. Install uv (if you don’t have it)

    Already installed? Check first · Open Terminal, type this command and press Enter

    uv --version
    • A version number such as uv … = installed, skip this step
    • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
    How to open Terminal

    Mac: press ⌘ + Space, type Terminal, press Enter

    Windows: open Start, type Windows PowerShell, then Open

    Not installed: uv has no click-through installer. Copy the one-line command for your system (macOS or Windows) from uv’s official page into Terminal · no separate Python install needed; uv downloads it when required

    Open the uv download page ↗

    When it’s done, close Terminal, open it again and run the same command. You should see a version number: uv --version

    Install once; it works for everything that needs uv

  2. Click this button to open Cursor

    Open in Cursor

    Cursor asks you to confirm; click Install

  3. Open the AI chat in Cursor in Agent mode

  4. Try it

    Use Vivado MCP Native and tell me what you can do for me, then show me one thing

    ✓ If Cursor says it is using Vivado MCP Native or shows a Vivado MCP Native tool in the answer, you are connected

2 optional setting(s) (works without them)

The command above works without these. Add them only if you want to change something, following the maker’s description.

  • VIVADO_PATH Optional path to a Vivado launcher, bin directory, or version directory.
  • VIVADO_MCP_OUTPUT_ENCODING Optional Vivado Tcl console output encoding, such as utf-8 or gbk.

Descriptions are as written by the maker.

Menu names checked against Cursor’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Works with VS Code, with some setup first

Install Python (uv) on your computer first (one time)

Let AI install it

Copy this message into a VS Code chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.

Please install the MCP server Vivado MCP Native for VS Code on this computer, in this order: 1) Check uv with uv --version. If it is missing, tell me to install it from https://docs.astral.sh/uv/getting-started/installation/; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "servers": { "vivado-native": { "type": "stdio", "command": "uvx", "args": [ "vivado-mcp-native" ] } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) No key is needed. 5) Do what we agreed, then check that the Vivado MCP Native tools really show up.

This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.

  1. Install uv (if you don’t have it)

    Already installed? Check first · Open Terminal, type this command and press Enter

    uv --version
    • A version number such as uv … = installed, skip this step
    • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
    How to open Terminal

    Mac: press ⌘ + Space, type Terminal, press Enter

    Windows: open Start, type Windows PowerShell, then Open

    Not installed: uv has no click-through installer. Copy the one-line command for your system (macOS or Windows) from uv’s official page into Terminal · no separate Python install needed; uv downloads it when required

    Open the uv download page ↗

    When it’s done, close Terminal, open it again and run the same command. You should see a version number: uv --version

    Install once; it works for everything that needs uv

  2. Click this button to open VS Code

    Open in VS Code

    VS Code asks you to confirm; click Install

  3. Open the AI chat in VS Code in Agent mode

  4. Try it

    Use Vivado MCP Native and tell me what you can do for me, then show me one thing

    ✓ If VS Code says it is using Vivado MCP Native or shows a Vivado MCP Native tool in the answer, you are connected

2 optional setting(s) (works without them)

The command above works without these. Add them only if you want to change something, following the maker’s description.

  • VIVADO_PATH Optional path to a Vivado launcher, bin directory, or version directory.
  • VIVADO_MCP_OUTPUT_ENCODING Optional Vivado Tcl console output encoding, such as utf-8 or gbk.

Descriptions are as written by the maker.

Menu names checked against VS Code’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Other apps that use MCP, such as Windsurf, Zed or Gemini CLI, each add servers differently. See how in the app list.

See every app that uses MCP →

JSON settings are under “For developers” below

Stuck? Ask people who use Vivado MCP Native💬 Discussion →
For developers: Terminal commands and JSON settings

Installed on your computer

Claude Code

claude mcp add --scope user vivado-native -- uvx vivado-mcp-native

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "vivado-native": {
      "command": "uvx",
      "args": [
        "vivado-mcp-native"
      ]
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "vivado-native": {
      "command": "uvx",
      "args": [
        "vivado-mcp-native"
      ]
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "vivado-native": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "vivado-mcp-native"
      ]
    }
  }
}

Values you fill in

  • VIVADO_PATH env
    Optional path to a Vivado launcher, bin directory, or version directory.
  • VIVADO_MCP_OUTPUT_ENCODING env
    Optional Vivado Tcl console output encoding, such as utf-8 or gbk.

Descriptions are as written by the maker.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

At a glance

Downloads per weeki
58/wk
Connection
Runs on your computer
Latest versioni
0.2.1
Published to registryi
Jul 27, 2026
Code last changedi
Jul 28, 2026
Maker
Arthurzxy
Packages
pypi: vivado-mcp-native
Registry status
Active

Which apps can use it

Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.

Run on your computer in

ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast

All apps, with pros and cons →

Related guides

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 19, 2026

  • ✓ Pass

    Maker matches the repo

    The registry name was verified with the GitHub account Arthurzxy, which owns the repo

  • ✓ Pass

    Still maintained

    Code last changed 4 months ago

  • ✓ Pass

    Has a licence

    Uses MIT

  • – Not applicable

    Endpoint responds

    This one runs on your computer; there is no internet endpoint

  • – Not applicable

    Sign-in with OAuth

    Runs on your computer and uses local settings instead

  • … Not checked yet

    No hidden instructions in tool descriptions

    Runs on your computer; we can only read tool lists from internet endpoints

Published vulnerabilities (OSV.dev)

No entries on OSV.dev for vivado-mcp-native@0.2.1

Checks only this package version, not every dependency · checked Nov 16, 2026

What we check → · JSON

Makers: ask for a re-check or report wrong info
For makers: add a badge to your README

If you made this, paste this code into your README. The badge links back to this page.

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/arthurzxy-vivado-mcp-native.svg)](https://mcp.popnx.com/en/servers/arthurzxy-vivado-mcp-native)

Discussion

Ask, share a tip or report that it does not work. Sorted by what people marked helpful.

No posts yet. Be the first to ask or share.

Posts here are written by users, not the PopNx team.

Sign in to post

User reviews

No reviews yet

Sign in to write a review

Compared with others in Developer toolsi

  • More stars than 0% of the other 6116 servers in this category
  • Published to the registry more recently than 22% of the other 6116 servers in this category
  • Basic checks equal to or better than 99% of the other 6116 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is Vivado MCP Native safe?

It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

The registry does not list a required key, though some servers ask you to sign in on first use.

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed 4 months ago, and the latest version (0.2.1) reached the registry 4 months ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.

What can I use instead?

In the same category: GitDiagram, Appllama, Cloudflare MCP, Omnara, Repowise

Similar alternatives

Same category, other makers, commands already checked. Official ones first, then by stars.

Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

GitDiagram

Architecture diagrams, explanations and Mermaid source for public GitHub repositories.

by ahmedkhaleel2004Widely used★ 19KUpdated 2 months ago

Runs in the cloud✓ service owner · gitdiagram.comTried by the PopNx team

Appllama

Study screens, flows and paywalls from top-earning iOS apps, then build from what wins.

by AppllamaWidely used★ 5.2KUpdated 3 months ago

Runs in the cloud✓ service owner · appllama.io

Repowise

Codebase intelligence for AI coding agents: graph, git history, docs, decisions, code health.

by repowise-devWidely used↓ 6.5K/wk★ 8.2K Stars for the whole repoUpdated 6 days ago

Computer or cloud✓ service owner · repowise.dev
Compared with similar ones
This one
Vivado MCP Native
GitDiagramAppllamaCloudflare MCPOmnaraRepowise
Runs whereInstalls on your computerRuns in the cloud, nothing to installRuns in the cloud, nothing to installRuns in the cloud, nothing to installRuns in the cloud, nothing to installCloud or install on your computer
Needs a keyNoNoNoNoNoNo
Add with + in ClaudeNoNoNoYesNoNo
Basic checks3/34/44/44/44/45/5
LicenseMITMITMITApache-2.0Apache-2.0AGPL-3.0
PriceNo cost listed in the registryNo cost listed in the registryNo cost listed in the registryNo cost listed in the registryNo cost listed in the registryNo cost listed in the registry

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

简体中文 | English

Vivado MCP Native

让 Claude、Cursor、Cline、Cherry Studio 等兼容 MCP 的 AI 客户端

在 Windows 和 Linux 上直接启动、控制并分析 AMD/Xilinx Vivado。

让 AI 处理 Vivado 的重复操作、报告读取和 Tcl 调用,你可以把精力放在 FPGA 架构、约束和问题判断上。

Vivado MCP Native 是一个面向 AMD/Xilinx Vivado 的本地 Model Context Protocol(MCP)服务器。它通过持久化 Vivado Tcl 会话,让 AI 客户端能够打开工程、运行综合与实现、生成比特流、读取时序和资源报告、控制仿真,并执行高级 Tcl 命令。

项目使用 Python subprocess 原生管理 Vivado 进程,可直接运行于 Windows 和 Linux,不依赖仅适用于类 Unix 环境的 pexpect。MCP 与 Vivado 都运行在用户本机,工程文件不会因为使用本项目而自动上传到云端。

[!IMPORTANT]

本项目不包含 Vivado。可用器件、IP、综合/实现功能和许可证能力,取决于本机安装的 AMD/Xilinx Vivado。

[!WARNING]

PyPI 上的 vivado-mcp 属于另一个项目。本项目的安装包名称是 `vivado-mcp-native`。


它可以做什么

类别主要能力典型用途
Vivado 会话启动、停止、健康检查、状态统计、异常恢复让 AI 复用同一个 Vivado Tcl 进程,避免每条命令都重新启动 Vivado
工程管理打开/关闭 .xpr 工程、读取工程信息检查目标器件、顶层模块、工程目录和当前工程状态
设计流程运行综合、实现、生成比特流自动执行 synth_1、impl_1 和 bitstream 流程,并核对实际运行状态
时序分析获取 WNS、TNS、WHS、THS 和关键路径判断是否满足时序,定位 setup/hold 违例及跨时钟问题
资源分析查询 LUT、FF、BRAM、DSP、IO 使用率判断设计是否放得下,分析资源热点和层次化占用
消息诊断获取 ERROR、CRITICAL WARNING、WARNING汇总综合和实现阶段的问题,辅助确定排查顺序
设计查询查询层次结构、端口、网络和单元核对综合后的连接关系、模块实例和信号名称
Vivado 仿真启动/重启/步进仿真、读取信号、设置断点运行 xsim,查看 testbench、波形对象和指定信号值
Tcl 扩展执行任意 Vivado Tcl 命令调用尚未封装为专用 MCP 工具的 Vivado 能力
大型报告生成完整报告并按区段读取避免超长报告一次性占满 AI 上下文窗口
可以直接对 AI 这样说
启动 Vivado,并检查当前会话是否健康。

打开 D:\FPGA\my_project\my_project.xpr,告诉我目标器件、顶层模块和当前运行状态。

运行综合,使用 8 个并行任务。完成后汇总 ERROR、CRITICAL WARNING 和资源利用率。

分析当前设计的时序,告诉我 WNS/TNS 是否满足,并列出最差的 10 条 setup 路径。

只分析 clk_250m 时钟域中经过 u_tdc 的失败路径,并给出可能的优化方向。

运行实现并生成 bitstream;每一步都确认 Vivado 的真实 STATUS 和 PROGRESS。

启动行为级仿真,运行 1 us,然后读取 /tb/dut/data_out 和 /tb/dut/valid。

执行 Tcl:report_drc -ruledecks default,并总结需要优先处理的问题。


为什么使用这个项目

常见问题Vivado MCP Native 的处理方式
Windows 下传统 pexpect 方案难以直接运行使用原生 subprocess 启动 vivado.bat、vivado.cmd 或 Linux vivado
Vivado 启动慢多次 MCP 调用复用同一个持久 Tcl 会话
Tcl 中包含引号、花括号、反斜杠或中文路径使用 UTF-8 十六进制传输和唯一命令标记进行可靠分帧
本地化 Vivado 提示符可能变化不依赖 Vivado% 提示符解析命令边界
长命令超时后容易留下 Vivado 子进程超时后清理完整进程树,避免残留失步会话
报告太长,AI 无法一次读完支持完整报告落盘并按行或正则表达式分段读取
不确定 Vivado 路径和编码是否正确提供 vivado-mcp-native-doctor 一键诊断

环境要求

组件要求
操作系统Windows 10/11 或 Linux
Python3.10–3.12
Vivado本机已经安装 AMD/Xilinx Vivado
许可证覆盖计划使用的器件、IP 和设计流程
MCP 客户端支持本地 stdio MCP Server

安装

方式一:使用 pip 安装

Windows PowerShell:

py -m pip install --upgrade vivado-mcp-native

Linux:

python3 -m pip install --upgrade vivado-mcp-native

检查安装结果:

py -m pip show vivado-mcp-native

vivado-mcp-native-doctor --help

方式二:使用 pipx 安装(推荐)

pipx 会为 MCP Server 创建独立 Python 环境,减少与其他 Python 包的依赖冲突。

Windows:

py -m pip install --user --upgrade pipx

py -m pipx ensurepath py -m pipx install vivado-mcp-native

Linux:

python3 -m pip install --user --upgrade pipx

python3 -m pipx ensurepath python3 -m pipx install vivado-mcp-native

升级:

py -m pipx upgrade vivado-mcp-native
方式三:直接从 GitHub 安装

安装 master 分支最新源码:

py -m pip install --upgrade "git+https://github.com/Arthurzxy/vivado_mcp_native.git@master"

使用 pipx:

py -m pipx install --force "git+https://github.com/Arthurzxy/vivado_mcp_native.git@master"

不依赖本机 Git,也可以安装 GitHub ZIP:

py -m pip install --upgrade "https://github.com/Arthurzxy/vivado_mcp_native/archive/refs/heads/master.zip"

用于开发或修改源码:

git clone https://github.com/Arthurzxy/vivado_mcp_native.git

cd vivado_mcp_native py -m pip install -e .

安装后提供的命令
命令作用
vivado-mcp-native启动 MCP stdio Server
vivado-mcp-native-doctor检查 Python、Vivado、Tcl 和 Unicode 通信
vivado-mcp-win兼容旧配置的 Server 别名
vivado-mcp-win-doctor兼容旧配置的 Doctor 别名

快速开始

第一步:确认 Vivado 启动文件

VIVADO_PATH 可以指向:

  • 完整启动文件:vivado.bat、vivado.cmd、vivado.exe 或 Linux vivado;
  • Vivado 的 bin 目录;
  • Vivado 版本目录。

Windows 示例:

$env:VIVADO_PATH = "D:\Software\Xilinx\2025.2.1\Vivado\bin\vivado.bat"

Linux 示例:

export VIVADO_PATH="/tools/Xilinx/Vivado/2025.2/bin/vivado"

未显式配置时,Server 会检查系统 PATH 和常见安装目录。

第二步:运行 Doctor
vivado-mcp-native-doctor --vivado-path "D:\Software\Xilinx\2025.2.1\Vivado\bin\vivado.bat"

机器可读 JSON 输出:

vivado-mcp-native-doctor --vivado-path "D:\Software\Xilinx\2025.2.1" --json

Doctor 会依次检查:

  1. Vivado 启动文件解析;
  2. 持久 Tcl 会话启动;
  3. Vivado 和 Tcl 版本查询;
  4. Tcl 表达式执行;
  5. 中文 Unicode 往返;
  6. 会话健康状态;
  7. Vivado 正常关闭。

Doctor 不会打开或修改用户工程。

第三步:配置 MCP 客户端

先查找安装后的命令路径:

(Get-Command vivado-mcp-native).Source
使用已安装的命令

把下面的 command 和 VIVADO_PATH 替换为你的实际路径:

{

"mcpServers": { "vivado": { "command": "C:\\Users\\you\\.local\\bin\\vivado-mcp-native.exe", "env": { "VIVADO_PATH": "D:\\Software\\Xilinx\\2025.2.1\\Vivado\\bin\\vivado.bat" } } } }

使用 Python 模块启动

适用于虚拟环境或 pip install 后不方便定位命令的情况:

{

"mcpServers": { "vivado": { "command": "C:\\Users\\you\\AppData\\Local\\Programs\\Python\\Python311\\python.exe", "args": ["-m", "vivado_mcp"], "env": { "VIVADO_PATH": "D:\\Software\\Xilinx\\2025.2.1\\Vivado\\bin\\vivado.bat" } } } }

建议使用可执行文件的绝对路径,避免 MCP 客户端与终端使用不同 PATH。

配置保存后,完全退出并重新启动 MCP 客户端,然后让 AI 执行:

检查 Vivado MCP 的主机状态,启动会话并返回 Vivado 版本。

推荐使用流程

1. vivado-mcp-native-doctor     检查本机环境
  1. start_session 启动持久 Vivado Tcl 会话
  2. open_project 打开 .xpr 工程
  3. get_project_info 确认器件、工程和顶层信息
  4. run_synthesis 运行综合
  5. get_messages 查看错误和警告
  6. get_timing_summary 检查 WNS/TNS/WHS/THS
  7. get_utilization 检查 LUT/FF/BRAM/DSP/IO
  8. run_implementation 运行布局布线
  9. get_timing_paths 分析最差路径
  10. generate_bitstream 生成比特流
  11. stop_session 关闭 Vivado 并释放资源

综合和实现可能耗时较长。大型工程应在调用时增加 timeout,并根据 CPU 和内存情况设置合适的 jobs。


MCP 工具说明

会话管理
  • start_session:启动持久 Vivado Tcl 会话;
  • stop_session:正常关闭 Vivado;
  • session_status:查看命令数、错误数和会话统计;
  • check_session_health:检查会话响应并按需恢复;
  • get_host_status:查看主机名、可用内存和会话状态。
工程与设计流程
  • open_project / close_project:打开或关闭 .xpr 工程;
  • get_project_info:获取当前工程信息;
  • run_synthesis:运行综合并验证 Vivado 的实际状态;
  • run_implementation:运行 place and route;
  • generate_bitstream:为已实现设计生成 bitstream。
报告与设计查询
  • get_timing_summary:返回 WNS、TNS、WHS、THS 等结构化指标;
  • get_timing_paths:按时钟、起点、终点或 through 对象过滤关键路径;
  • get_utilization:返回 LUT、FF、BRAM、DSP 和 IO 使用率;
  • get_clocks:获取时钟与约束信息;
  • get_messages:分类读取 ERROR、CRITICAL WARNING 和 WARNING;
  • get_design_hierarchy:读取综合后设计层次;
  • get_ports / get_nets / get_cells:查询端口、网络和单元。
仿真
  • set_simulation_top:设置 testbench 顶层;
  • launch_simulation:启动行为级或综合/实现后仿真;
  • run_simulation / step_simulation / restart_simulation:运行、步进或重启;
  • get_signal_value / get_signal_values:读取一个或一组信号;
  • get_scopes / get_simulation_objects:浏览仿真层次和对象;
  • add_signals_to_wave:添加波形信号;
  • add_breakpoint / remove_breakpoints:管理仿真断点;
  • get_simulation_messages:读取仿真日志;
  • close_simulation:关闭仿真。
高级能力
  • run_tcl:执行任意 Vivado Tcl;
  • generate_full_report:生成 timing、utilization、power、DRC 等完整报告;
  • read_report_section:按行范围或正则表达式读取大型报告;
  • request_feature / list_feature_requests:记录当前未覆盖的功能需求。

工作原理

Claude / Cursor / Cline / Cherry Studio / 其他 MCP 客户端

│ │ MCP stdio / JSON-RPC ▼ Vivado MCP Native │ │ 持久 subprocess Tcl 会话 ▼ AMD/Xilinx Vivado -mode tcl │ ▼ 本机 FPGA 工程与报告

每条 Tcl 命令会使用 UTF-8 十六进制编码并附加唯一标记。Server 分别提取标准输出、Tcl 返回值、返回码和错误栈,不依赖可能随语言环境变化的 Vivado% 提示符。


常见问题

找不到 vivado-mcp-native 命令
py -m pipx ensurepath

(Get-Command vivado-mcp-native).Source

重启终端或把返回的绝对路径直接写入 MCP 客户端配置。

找不到 Vivado

先验证启动文件:

& "D:\Software\Xilinx\2025.2.1\Vivado\bin\vivado.bat" -mode tcl

随后运行:

vivado-mcp-native-doctor --vivado-path "D:\Software\Xilinx\2025.2.1\Vivado\bin\vivado.bat"
中文输出乱码
$env:VIVADO_MCP_OUTPUT_ENCODING = "gbk"

可设置为 utf-8、gbk,或与本机 Vivado Tcl 控制台一致的编码。

综合或实现超时

超时后 Server 会终止完整 Vivado 进程树,防止继续使用已经失步的会话。重新启动会话,并为大型工程设置更长的 timeout。

vivado-mcp 和 vivado-mcp-native 是同一个包吗

不是。安装本项目请始终使用:

py -m pip install vivado-mcp-native

更多 Windows 配置说明参见 WINDOWS_INSTALL.md。


安全说明

run_tcl 可以按当前用户权限执行任意 Tcl,包括读写文件和启动外部程序。请注意:

  • 只连接可信的 MCP 客户端和模型;
  • 执行删除文件、重置工程或覆盖输出前检查目标路径;
  • 对重要工程使用版本控制并保留备份;
  • 不要把没有鉴权和隔离的 Vivado MCP 直接暴露到公网。

官方 MCP Registry

官方 Registry 标识:

io.github.Arthurzxy/vivado-mcp-native

注册元数据位于 server.json,当前发布版本为 0.2.1,传输方式为本地 stdio。


贡献

欢迎通过 Issue 或 Pull Request:

  • 补充新的 Vivado 工具;
  • 改进不同 Vivado 版本的兼容性;
  • 增强报告解析;
  • 补充 MCP 客户端配置示例;
  • 修正文档或翻译。

许可证与致谢

本项目使用 MIT License。