mcpField
M
mcp-sandpiperaas

mcp-sandpiperaas

Local
github.com/shariethernetDeveloper Tools3Updated 77w ago
Repository

About mcp-sandpiperaas

mcp-sandpiperaas connects MCP clients to Redwood EDA’s SandPiper-SaaS compiler, converting TL-Verilog files into SystemVerilog or Verilog. It is intended for hardware design workflows that need compiler options exposed for inspection and automation.

Key features

  1. 01Compile TL-Verilog to SystemVerilog or Verilog
  2. 02Expose SandPiper flags as tool parameters
  3. 03Support compiler automation via natural-language requests

Use cases

  1. 01Convert TL-Verilog designs into Verilog outputs
  2. 02Inspect and automate compiler option selection

MCP support

The MCP server exposes SandPiper-SaaS compilation through a tool, with each compiler flag available as a parameter. It runs over stdio and accepts tool-list and tool-invocation requests.

#verilog#systemverilog#tl-verilog#mcp-server

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

mcp-sandpiperaas

A MCP server that wraps Redwood EDA’s SandPiper-SaaS compile function to convert TL‑Verilog (TLV) files into SystemVerilog/Verilog. Exposes every SandPiper flag as its own MCP tool parameter for introspection and easy automation. In other words, tell in natural language(English) what you want the compiler to do. Refer prompt for prompt examples.

This project uses UV to manage its virtual environment and dependencies.

Install UV

If you don’t already have the UV CLI installed, you can install it using just pip (no pipx required):

pip install --user uv

Or, if you prefer an isolated install via pipx:

pipx install uv

Verify that it’s on your PATH:

uv --version
Initialize & install dependencies & install dependencies

Clone this repo

git clone https://github.com/shariethernet/mcp-sandpipersaas.git

From the project root, run:

uv install

This will create (or reuse) a .venv/ directory and install all required packages.

Running the server

With uv

The easiest way to start the MCP server is via the uv command (part of the UV toolkit):

uv --directory <path_to_this_repo>/mcp-sandpiperasaas run mcp-sandpiperasaas.py

This will launch the MCP server over stdio, ready to accept tools/list and tools/invoke requests.

With uvx

If you prefer the lightweight uvx bundle:

uvx run mcp-sandpiperasaas.py

It will detect and run the MCP server in the current directory.

Claude Desktop/Cline configuration

You can configure your MCP-server with the following json for Cline or Claude Desktop or any MCP Client that atleast supports mcp tool calling: (Note for paths in windows use \\ instead of /)

{
  "mcp-sandpiperasaas": {
    "command": "uv",
    "args": [
      "--directory",
      "<path to this repo>/mcp-sandpiperasaas",
      "run",
      "mcp-sandpiperasaas.py"
    ],
    "autoApprove": [
      "sandpiper_compile"
    ]
  }
}
  • command: the CLI you use (uv or uvx)
  • args: arguments to point at the project folder and mcp script
  • autoApprove: list of tool names that can run without extra confirmation (“sandpiper_compile”)

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.