MCP.Market

Neosyn Fpga MCP server

by neosyn.io·io.neosyn/neosyn-fpga-mcp·v1.4.0·1 stars

AI-agent MCP server for FPGA design: compile, validate & generate Verilog from C⏚ HDL.

A86/100grade A
What users say
No reviews yet
Be the first
Safety scan
A86/100

full report

Adoption
Growing

1 stars61 downloads/wk

Reviews

Write one

Nobody has reviewed Neosyn Fpga yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Neosyn Fpga tools

No tool declarations could be read from the package source. They show once the server is installed.

Public scan report

scanner v0.1.10 · 2026-10-16 · same rubric, same numbers if you re-run it

no findings
  • Code scan6 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 16 days ago15/15
  • Maintainer identitynamespace and repository owner differ4/10
Overall 86/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Neosyn Fpga compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
86/100
higher than 75% of 4,461 AI and agents servers
GitHub stars
1
more than 50% of 2,713 AI and agents servers
Downloads a week
61
more than 48% of 1,554 AI and agents servers with a package

Release history: 4 versions in the registry since 2026-09-20, latest 2026-09-30, typically one every 3 days.

Install Neosyn Fpga in Claude Code, Cursor or VS Code

claude mcp add neosyn-fpga-mcp -- uvx neosyn-fpga-mcp
Add to Cursor

What the publisher says

From the Neosyn Fpga repository's README, as published. We do not edit it. Read it on GitHub

C⏚ Agent Kit

<!-- mcp-name: io.neosyn/neosyn-fpga-mcp -->

Install neosyn-fpga-mcp. This project was called cg-agent-kit up to

1.0.0. "cg" is our shorthand for C⏚ and meant nothing to anyone searching for

an FPGA tool.

pip install cg-agent-kit does not work — that name has never been

published to PyPI, so every instruction pointing at it, including our own,

returned No matching distribution found. We intend to claim it as a shim

that pulls in this package; until then, neosyn-fpga-mcp is the only name

that installs.

Inside the package the old paths are intact:

python -m cgagentkit.cgmcpserver and the cg-mcp-server command both

still resolve, so an existing MCP host config keeps working once this package

is installed.

Make any LLM write C⏚ (Cg) instead of Verilog — without retraining the model. The kit has two parts that work together:

model's system prompt and it can write plausible C⏚: the mental model, types, ports, structs/enums/generics, the standard library, and the gotchas that otherwise sink first drafts.

  1. cgcontext.md** — a paste-anywhere knowledge pack. Load it as the

checks, simulates, and generates Verilog against the real compiler and self-corrects. This is what makes the output actually correct despite the model having almost no C⏚ in its training data.

  1. cgmcpserver.py — the Neosyn compiler exposed as MCP tools. The model

Knowledge gives a good first draft; the compiler-in-the-loop makes it right. Both are model-agnostic — any MCP-capable host (Claude Desktop/Code, Cursor, Cline, …) works, and the context pack works with any LLM at all.

Why this instead of fine-tuning

C⏚ is a niche language with little public code, and it gains features every release. A fine-tuned model is expensive and goes stale. In-context knowledge plus a verification loop costs nothing to retrain, tracks the language as the compiler evolves, and converges on correct code by running it rather than recalling it.

Tools the server exposes

13 tools. Every tool that takes source accepts source (a C⏚ string) and an optional extra_files map ({"Defs.cg": "..."}) for imported bundles/tasks.

These are the only names that exist, and the server says so rather than hoping you read this table: a call to a tool that does not exist comes back with the whole list and the closest real name (cgcompile → "did you mean cgcheck?"), cg_capabilities carries the list, and the first call of a session carries it once. The list is generated from the tool registry, so it cannot drift out of step with the table below — TestNoStaleToolNames and TestStaticRostersMatchTheRegistry fail if it does.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Neosyn Fpga: common questions

Is Neosyn Fpga MCP server safe?
Yes, by our scan: it is graded A (86/100). Read the Neosyn Fpga safety report
How do I install Neosyn Fpga?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Neosyn Fpga need an API key?
No secret keys are declared. It reads 1 setting from the environment.
Is Neosyn Fpga maintained?
The last commit was 36 days ago (2026-09-30). The latest release is v1.4.0.
What can I use instead of Neosyn Fpga?
Servers from other publishers that do the same job: Figma Context MCP server, PaperBanana MCP server and Agent-Native Slides MCP server.
How does Neosyn Fpga compare with other AI and agents MCP servers?
safety score 86/100 (higher than 75% of 4,461 AI and agents servers); github stars 1 (more than 50% of 2,713 AI and agents servers); downloads a week 61 (more than 48% of 1,554 AI and agents servers with a package). Full comparison.

Alternatives to Neosyn Fpga

Same job from other publishers: the closest match first, then the best rated.

  • Figma Context
    Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
    B
  • PaperBanana
    Generate academic diagrams and statistical plots from text using multi-agent AI.
    A
  • Agent-Native Slides
    Agent-Native Google Slides - generate and edit React presentations
    A
  • Roast My Design System
    Audit your Design System and serve your Agent the rules that keep AI-written UI on-system.
    A
  • Kiln
    Spawn an object into existence: describe it, and your agent designs it, checks it, and 3D prints it.
    B