MCP for Vivado MCP Server

Local setup required. This server has to be cloned and prepared on your machine before you register it in Claude Code.
1

Set the server up locally

Run this once to clone and prepare the server before adding it to Claude Code.

Run in terminal
git clone https://github.com/lzw12123/mcp-for-vivado
cd mcp-for-vivado

Then follow the repository README for any remaining dependency or build steps before continuing.

2

Register it in Claude Code

After the local setup is done, run this command to point Claude Code at the built server.

Run in terminal
claude mcp add mcp-for-vivado -- python "<FULL_PATH_TO_MCP_FOR_VIVADO>/dist/index.js"

Replace <FULL_PATH_TO_MCP_FOR_VIVADO>/dist/index.js with the actual folder you prepared in step 1.

README.md

An AI-centric MCP workbench for automating Xilinx Vivado workflows.

MCP for Vivado

面向 AI 的 Vivado MCP 工作台。
本项目采用 MCP-first 设计,不提供自研桌面 GUI;Vivado 相关操作必须在真实 Vivado GUI 中执行,并在关键步骤切到对应可视上下文。

当前状态

  • 版本:v1
  • 验收结论:有条件通过,可发布
  • 当前已知非阻塞项:
    • V1-DEFECT-006
    • OPT-001

适用场景

  • 由 AI 调用 MCP 方法,驱动 Vivado 工程主流程
  • 自动发现本机 Vivado 版本并完成 workspace 级绑定
  • 打开工程、添加源码/约束、运行综合/实现、读取时序与资源摘要
  • 在 Vivado GUI 中显示关键步骤对应的上下文

目录说明

快速开始

  1. 安装 Python 3.11+
  2. 安装 Vivado,并确保版本不低于 2018.3
  3. 执行:
cd D:\ai_playgraund\vivado_mcp
powershell -ExecutionPolicy Bypass -File .\scripts\install_mcp_for_ai.ps1
  1. docs/USER_INSTALL_AND_USAGE.mddocs/AI_INSTALL_AND_USAGE.md 开始使用

当前入口

当前 v1 暴露的是 Python 进程内 MCP 风格入口:

核心类:

  • fpga_mcp.FpgaMcpServer

说明:

  • 当前仓库提供的是“方法注册 + 协议返回壳 + orchestration 接线”的 v1 入口
  • 不是一个独立的 stdio / HTTP 传输层服务
  • 若要接入外部 AI 宿主,可在宿主中直接导入 FpgaMcpServer 并调用 list_methods() / invoke()

Tools (4)

manage_projectOpen Vivado projects and manage workspace bindings.
modify_designAdd source files or constraints to the current Vivado project.
run_workflowExecute synthesis or implementation processes in Vivado.
get_summaryRetrieve timing analysis and resource utilization summaries.

Configuration

claude_desktop_config.json
{"mcpServers": {"vivado": {"command": "python", "args": ["path/to/server.py"]}}}

Try it

Open the Vivado project located at D:/projects/fpga_design and bind it to the current workspace.
Add the new constraints file constraints.xdc to the active project.
Run the synthesis process and report any timing violations found.
Provide a summary of the resource utilization for the current implementation.

Frequently Asked Questions

What are the key features of MCP for Vivado?

Automated discovery of local Vivado versions and workspace binding. Programmatic control over project opening and file management. Execution of synthesis and implementation workflows via AI. Extraction of timing analysis and resource utilization reports. Integration with Vivado GUI for visual context during AI operations.

What can I use MCP for Vivado for?

Automating repetitive FPGA build and synthesis cycles. Assisting hardware engineers in debugging timing closure issues. Managing complex Vivado project structures via natural language commands. Integrating FPGA design workflows into broader AI-driven CI/CD pipelines.

How do I install MCP for Vivado?

Install MCP for Vivado by running: powershell -ExecutionPolicy Bypass -File .\scripts\install_mcp_for_ai.ps1

What MCP clients work with MCP for Vivado?

MCP for Vivado works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep MCP for Vivado docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Need the old visual installer? Open Conare IDE.
Open Conare