fpgaZeroMCP

fpgaZeroMCP

An open-source Model Context Protocol server that gives AI assistants a complete FPGA toolchain — lint, simulate, synthesize, place-and-route, and a live IP core registry backed by GitHub.

Ask your AI to search for cores, pull them in, lint HDL, synthesize a design, or run a simulation — all without leaving your chat window.

Table of Contents

• How it works
• Prerequisites
• Installation
• MCP Client Setup
• Tools
• IP Core Registry
• Synthesis Targets
• LiteX
• Local Core Repositories
• Standalone / Scripting
• core.json Schema
• License

How it works

Your AI assistant  <-->  fpgaZeroMCP (stdio MCP server)  <-->  OSS tools
                                    |
                           cores/   registry on GitHub
                           (uart_tx, fifo + any imported)

The MCP server runs as a local subprocess. Your AI calls tools on it over JSON-RPC (stdio). The server shells out to Yosys, nextpnr, iverilog, Verilator, and others from OSS CAD Suite — and can pull any MIT-licensed FPGA core directly from GitHub.

Prerequisites

Add OSS CAD Suite to your PATH after installing. All tool wrappers degrade gracefully if a tool is missing.

Installation

git clone https://github.com/your-org/fpgaZeroMCP
cd fpgaZeroMCP
pip install -e .

MCP Client Setup

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "fpgaZeroMCP": {
      "command": "python",
      "args": ["/path/to/fpgaZeroMCP/server.py"],
      "env": { "PYTHONPATH": "/path/to/fpgaZeroMCP" }
    }
  }
}

VS Code (GitHub Copilot)

Add to .vscode/mcp.json in your workspace:

{
  "servers": {
    "fpgaZeroMCP": {
      "type": "stdio",
      "command": "python",
      "args": ["/path/to/fpgaZeroMCP/server.py"],
      "env": { "PYTHONPATH": "/path/to/fpgaZeroMCP" }
    }
  }
}

Cursor / Windsurf

Add to your MCP settings (Settings → MCP Servers):

{
  "fpgaZeroMCP": {
    "command": "python",
    "args": ["/path/to/fpgaZeroMCP/server.py"],
    "env": { "PYTHONPATH": "/path/to/fpgaZeroMCP" }
  }
}

Example prompts

• "Find me an I2C master core and import it."
• "Synthesize this design for ECP5 and tell me the LUT count."
• "Run place-and-route on this module targeting an iCE40 HX1K in a TQ144 package."
• "Lint this Verilog and fix any errors."
• "Simulate this FIFO with a testbench that writes 4 bytes then reads them back."
• "Format this SystemVerilog file."

Tools

HDL quality

Design flow

IP core registry

LiteX

IP Core Registry

Cores live in cores/<name>/ — a core.json manifest and one or more HDL files. The server auto-discovers them on startup and reloads after any import.

Two reference cores are included (uart_tx, fifo) to demonstrate the format. The registry is not meant to grow here — it is powered by GitHub.

Getting cores at runtime

# Find a RISC-V softcore
search_github_cores("riscv softcore", language="verilog")

# Pull it in
import_github_core("YosysHQ/picorv32")

# It is now in the local registry
get_ip_core("picorv32")
generate_ip("picorv32", {"COMPRESSED_ISA": 1})

The server automatically uses FuseSoC CAPI2 metadata (.core files) when found in the repo, giving richer parameter and port information. Only MIT-licensed GitHub repos are accepted.

Contributing a core

Do not open PRs adding cores to this repo. Instead:

1. Publish your HDL repo on GitHub with the fpga topic and an MIT license
2. Optionally add a FuseSoC CAPI2 .core file for richer metadata
3. Anyone can then import_github_core("you/your-core") directly

This keeps the server lean and lets the community grow organically on GitHub.

Synthesis Targets

Common device/package values for place_and_route:

LiteX

LiteX is a Python SoC framework that can target many FPGA boards. fpgaZeroMCP exposes three dedicated LiteX tools and also accepts backend="litex" in synthesize and place_and_route.

# Dedicated tools
litex_build(board="arty", args=["--build"])
litex_soc(board="arty", args=["--no-compile"])
litex_flow(board="arty", args=["--build", "--output-dir", "build_arty"])

# As a backend in existing flow tools
synthesize(code="...", top_module="top", backend="litex", litex_board="arty")
place_and_route(code="...", top_module="top", target="ice40", device="hx1k",
                backend="litex", litex_board="arty", litex_args=["--build"])

Local Core Repositories

You can point the registry at your own local HDL directories in two ways:

Environment variable:

Linux/macOS (colon-separated):

export USERCORES_PATH=/home/you/my-cores:/home/you/work-cores

Windows (semicolon-separated, PowerShell):

$env:USERCORES_PATH = "C:\Users\you\my-cores;C:\Users\you\work-cores"

Config file (~/.fpgazero_mcp/config.json):

{
  "core_paths": [
    "/home/you/my-cores",
    "/home/you/work-cores"
  ]
}

All paths are scanned on startup alongside the built-in cores/ directory.

Allowed licenses

By default, import_github_core accepts repos with any of these SPDX licenses:

MIT, GPL-2.0, GPL-3.0, LGPL-2.1, LGPL-3.0

Override with the FPGAZERO_ALLOWED_LICENSES environment variable (comma-separated SPDX IDs):

# Linux/macOS
export FPGAZERO_ALLOWED_LICENSES=MIT
export FPGAZERO_ALLOWED_LICENSES=MIT,Apache-2.0

# Windows (PowerShell)
$env:FPGAZERO_ALLOWED_LICENSES = "MIT"
$env:FPGAZERO_ALLOWED_LICENSES = "MIT,Apache-2.0"

License IDs follow SPDX notation. The check is done at import time; search_github_cores returns results regardless of license so you can evaluate before importing.

Standalone / Scripting

The Python API can be used directly without an MCP client:

from registry.resolver import CoreRegistry
from tools.lint import lint_hdl

reg = CoreRegistry()

# Import a core from GitHub
reg.import_github_core("ben-marshall/uart")

# Generate a parameterized instantiation
result = reg.generate_ip("uart", {"CLKS_PER_BIT": 868})
print(result["instantiation"])

# Lint some HDL
lint_hdl(open("my_design.v").read())

python example.py   # runs the built-in demo

core.json Schema

{
  "name": "my_core",
  "version": "1.0.0",
  "description": "...",
  "author": "you",
  "license": "MIT",
  "language": "verilog",
  "category": "communication",
  "tags": ["spi", "serial"],
  "parameters": {
    "DATA_WIDTH": { "type": "integer", "default": 8, "description": "..." }
  },
  "ports": {
    "clk": { "direction": "input", "width": 1, "description": "System clock" }
  },
  "files": ["my_core.v"]
}

Author

Leonardo Capossio (bard0) — [email protected]

License

MIT — see LICENSE.