Skip to main content
MCP server CX Codex

neosyn-fpga-mcp — Claude Code MCP server for FPGA development

Connect an AI coding agent to the C⏚ FPGA toolchain to check source code, run simulations, and produce Verilog for hardware development.

Install into Claude Code · Platform CLI All methods and platforms ↓
claude mcp add --env CG_JAR=<CG_JAR> --transport stdio neosyn-fpga-mcp -- uvx neosyn-fpga-mcp
Open on GitHub

What neosyn-fpga-mcp does

neosyn-fpga-mcp exposes C⏚ compiler and verification functions to AI agents over MCP. The agent can inspect compiler diagnostics, simulate a design, and generate Verilog files. Its cg_synth tool runs synthesis through Yosys, returning findings that help identify constant-folded logic or inferred latches.

The server works alongside cg_context.md, a language reference pack covering C⏚ types, ports, structures, and other language details. For a new design, cg_scaffold creates a compiling, self-checking starting structure with unfinished logic sections. A practical workflow is to compile first, simulate the design, and then inspect its synthesis results.

You need Python 3.10+, Java 17 or newer on PATH, and a C⏚ compiler JAR configured through CG_JAR. Install Yosys on PATH to use cg_synth; iverilog is needed when selecting the Icarus Verilog simulator. The bytecode simulator comes with the commercial distribution, which also requires a licence file configured through NEOSYN_CG_LICENSE or stored at the extension's default location.

What it helps with

  • Inspect C⏚ source code and resolve compiler diagnostics
  • Simulate hardware behavior and check output values
  • Generate Verilog files for an RTL workflow
  • Detect constant-folded logic or inferred latches during synthesis
  • Create a self-checking scaffold for a task, FSM, or stream

Example prompts for the agent

  • Check this C⏚ source with cg_check and fix the reported compiler issues.
  • Run cg_simulate on this hardware design and verify its outputs across test cycles.
  • Generate Verilog with cg_generate_verilog, then inspect the synthesis results using cg_synth.

How to install neosyn-fpga-mcp

Platform CLI

claude mcp add --env CG_JAR=<CG_JAR> --transport stdio neosyn-fpga-mcp -- uvx neosyn-fpga-mcp

Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from neosyn-fpga-mcp <command>

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about neosyn-fpga-mcp

How do I install neosyn-fpga-mcp in Claude Code?

Register the server with claude mcp add neosyn-fpga-mcp -- uvx neosyn-fpga-mcp. Then configure the compiler JAR using claude mcp add --env CG_JAR=<CG_JAR> --transport stdio neosyn-fpga-mcp -- uvx neosyn-fpga-mcp.

What does neosyn-fpga-mcp do?

It gives an AI agent MCP tools for compiling and simulating C⏚, generating Verilog, and checking synthesis. The returned diagnostics provide concrete feedback for revising hardware code.

Which dependencies does neosyn-fpga-mcp require?

The setup requires Python 3.10+, Java 17 or newer, and a C⏚ compiler JAR configured with CG_JAR. Yosys is needed for cg_synth, while iverilog is required when using the Icarus Verilog simulator.

Similar MCP servers

All MCP servers for Testing and QA →

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor