Skip to main content
Glama

ZigNet

MCP Server for Zig β€” Intelligent code analysis, validation, and documentation powered by a fine-tuned LLM

ZigNet integrates with Claude (and other MCP-compatible LLMs) to provide real-time Zig code analysis without leaving your chat interface.


🎯 Features

MCP Tools

Analyze Zig code for syntax errors, type mismatches, and semantic issues using zig ast-check.

Example usage:

User: "Analyze this Zig code"
Claude: [calls analyze_zig tool]
Response: "βœ… Syntax: Valid | Type Check: PASS | Warnings: 0"

Capabilities:

  • Lexical analysis (tokenization)

  • Syntax parsing (AST generation)

  • Type checking and validation

  • Semantic error detection

  • Line/column error reporting

Validate and format Zig code using zig fmt, generating clean, idiomatic output.

Example:

// Input (messy)
fn add(a:i32,b:i32)i32{return a+b;}

// Output (formatted)
fn add(a: i32, b: i32) i32 {
    return a + b;
}

Capabilities:

  • Code formatting (2-space indentation)

  • Syntax validation

  • Best practices enforcement

  • Preserves semantics

Retrieve Zig documentation and explanations for language features using a fine-tuned LLM.

Example:

Query: "comptime"
Response: "comptime enables compile-time evaluation in Zig..."

Powered by:

  • Fine-tuned Qwen2.5-Coder-7B model

  • 13,756 examples from Zig 0.13-0.15

  • Specialized on advanced Zig idioms (comptime, generics, error handling)

Get intelligent code fix suggestions for Zig errors using AI-powered analysis.

Example:

// Error: "Type mismatch: cannot assign string to i32"
var x: i32 = "hello";

// Suggestions:
// Option 1: var x: []const u8 = "hello";  // If you meant string
// Option 2: var x: i32 = 42;              // If you meant integer

Features:

  • Context-aware suggestions

  • Multiple fix options

  • Explanation of the issue

  • Zig idiom recommendations


πŸ“– Usage

ZigNet is an MCP server β€” configure it once in your MCP client, then use it naturally in conversation.

Configuration file location:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Linux: ~/.config/Claude/claude_desktop_config.json

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

Add this:

{
  "mcpServers": {
    "zignet": {
      "command": "npx",
      "args": ["-y", "zignet"]
    }
  }
}

Then restart Claude Desktop and start using:

You: "Analyze this Zig code for errors"
     [paste code]

Claude: [uses analyze_zig tool]
        "Found 1 type error: variable 'x' expects i32 but got []const u8"

Method 1: VS Code Marketplace (coming soon)

  1. Open VS Code Extensions (Ctrl+Shift+X / Cmd+Shift+X)

  2. Search for @mcp zignet

  3. Click Install

  4. Restart VS Code

Method 2: Manual configuration (available now)

  1. Install GitHub Copilot extension (if not already installed)

  2. Open Copilot settings

  3. Add to MCP servers config:

{
  "mcpServers": {
    "zignet": {
      "command": "npx",
      "args": ["-y", "zignet"]
    }
  }
}

Then restart VS Code and Copilot will have access to ZigNet tools.

What happens after configuration?

  1. First use: npx downloads and caches ZigNet automatically

  2. Zig compiler: Downloads on-demand (supports Zig 0.13, 0.14, 0.15)

  3. Tools available: analyze_zig, compile_zig (+ get_zig_docs, suggest_fix coming soon)

  4. Zero maintenance: Updates automatically via npx -y zignet


βš™οΈ Configuration

GPU Selection (Multi-GPU Systems)

If you have multiple GPUs (e.g., AMD + NVIDIA), you can control which GPU ZigNet uses via environment variables.

Windows (PowerShell):

$env:ZIGNET_GPU_DEVICE="0"
npx -y zignet

macOS/Linux:

export ZIGNET_GPU_DEVICE="0"
npx -y zignet

VS Code MCP Configuration with GPU selection:

{
  "mcpServers": {
    "zignet": {
      "command": "npx",
      "args": ["-y", "zignet"],
      "env": {
        "ZIGNET_GPU_DEVICE": "0"
      }
    }
  }
}

Claude Desktop configuration with GPU selection:

macOS/Linux (~/.config/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "zignet": {
      "command": "npx",
      "args": ["-y", "zignet"],
      "env": {
        "ZIGNET_GPU_DEVICE": "0"
      }
    }
  }
}

Windows (%APPDATA%\Claude\claude_desktop_config.json):

{
  "mcpServers": {
    "zignet": {
      "command": "npx",
      "args": ["-y", "zignet"],
      "env": {
        "ZIGNET_GPU_DEVICE": "0"
      }
    }
  }
}

GPU Device Values:

  • "0" - Use first GPU only (e.g., RTX 4090)

  • "1" - Use second GPU only

  • "0,1" - Use both GPUs

  • Not set - Use all available GPUs (default)

Identify your GPUs:

# NVIDIA GPUs
nvidia-smi

# Output shows GPU indices:
# GPU 0: NVIDIA RTX 4090
# GPU 1: AMD Radeon 6950XT (won't be used by CUDA anyway)

Advanced Configuration

All configuration options can be set via environment variables:

Variable

Default

Description

ZIGNET_GPU_DEVICE

auto

GPU device selection (CUDA_VISIBLE_DEVICES)

ZIGNET_GPU_LAYERS

35

Number of model layers on GPU (0=CPU only)

ZIGNET_MODEL_PATH

~/.zignet/models/...

Custom model path

ZIGNET_MODEL_AUTO_DOWNLOAD

true

Auto-download model from HuggingFace

ZIGNET_CONTEXT_SIZE

4096

LLM context window size

ZIGNET_TEMPERATURE

0.7

LLM creativity (0.0-1.0)

ZIGNET_TOP_P

0.9

LLM sampling parameter

ZIG_SUPPORTED

0.13.0,0.14.0,0.15.2

Supported Zig versions

ZIG_DEFAULT

0.15.2

Default Zig version

See .env.example for detailed examples.


πŸ—οΈ Architecture

β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚ Claude / MCP Client                                 β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                     β”‚ MCP Protocol (JSON-RPC)
β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β–Όβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚ ZigNet MCP Server (TypeScript)                      β”‚
β”‚  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”   β”‚
β”‚  β”‚ Tool Handlers                                β”‚   β”‚
β”‚  β”‚ - analyze_zig                                β”‚   β”‚
β”‚  β”‚ - compile_zig                                β”‚   β”‚
β”‚  β”‚ - get_zig_docs                               β”‚   β”‚
β”‚  β”‚ - suggest_fix                                β”‚   β”‚
β”‚  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜   β”‚
β”‚                β–Ό                                    β”‚
β”‚  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”   β”‚
β”‚  β”‚ Zig Compiler Integration                     β”‚   β”‚
β”‚  β”‚ - zig ast-check (syntax + type validation)   β”‚   β”‚
β”‚  β”‚ - zig fmt (official formatter)               β”‚   β”‚
β”‚  β”‚ - Auto-detects system Zig installation       β”‚   β”‚
β”‚  β”‚ - Falls back to downloading if needed        β”‚   β”‚
β”‚  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜   β”‚
β”‚                β–Ό                                    β”‚
β”‚  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”   β”‚
β”‚  β”‚ Fine-tuned LLM (Qwen2.5-Coder-7B)            β”‚   β”‚
β”‚  β”‚ - Documentation lookup                       β”‚   β”‚
β”‚  β”‚ - Intelligent suggestions                    β”‚   β”‚
β”‚  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜   β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜

Why this architecture?

  • Official Zig compiler (100% accurate, always up-to-date) instead of custom parser

  • System integration (uses existing Zig installation if available)

  • LLM-powered suggestions (get_zig_docs, suggest_fix) for intelligence

  • No external API calls (local inference via node-llama-cpp)

  • Fast (< 100ms for validation, < 2s for LLM suggestions)

Note: When Zig releases a new version (e.g., 0.16.0), ZigNet will need to re-train the LLM model on updated documentation and examples.


πŸ§ͺ Development Status

Component

Status

Notes

Zig Compiler Wrapper

βœ… Complete

ast-check + fmt integration

System Zig Detection

βœ… Complete

Auto-detects installed Zig versions

Multi-version Cache

βœ… Complete

Downloads Zig 0.13-0.15 on demand

MCP Server

βœ… Complete

All 4 tools fully implemented

LLM Fine-tuning

βœ… Complete

Trained on 13,756 Zig examples

get_zig_docs

βœ… Complete

LLM-powered documentation lookup

suggest_fix

βœ… Complete

LLM-powered intelligent suggestions

GGUF Conversion

βœ… Complete

Q4_K_M quantized (4.4GB)

E2E Testing

βœ… Complete

27/27 tests passing (8.7s)

Claude Integration

⏳ Planned

Final deployment to Claude Desktop

Current Phase: Ready for deployment - All core features complete


πŸ§ͺ Testing

Running Tests

# Run all tests (unit + E2E)
pnpm test

# Run only E2E tests
pnpm test tests/e2e/mcp-integration.test.ts

# Run deterministic tests only (no LLM required)
SKIP_LLM_TESTS=1 pnpm test tests/e2e

# Watch mode for development
pnpm test:watch

Test Coverage

E2E Test Suite: 27 tests covering all MCP tools

Tool

Tests

Type

Pass Rate

analyze_zig

4

Deterministic

100%

compile_zig

3

Deterministic

100%

get_zig_docs

5

LLM-powered

100%

suggest_fix

5

LLM-powered

100%

Integration

3

Mixed

100%

Performance

3

Stress tests

100%

Edge Cases

4

Error paths

100%

Execution time: 8.7 seconds (without LLM model, deterministic only)
With LLM model: ~60-120 seconds (includes model loading + inference)

Test Behavior

  • Deterministic tests (12 tests): Always run, use Zig compiler directly

  • LLM tests (15 tests): Auto-skip if model not found, graceful degradation

  • CI/CD ready: Runs on GitHub Actions without GPU requirements

For detailed testing guide, see tests/e2e/README.md


πŸ“¦ Project Structure

zignet/
β”œβ”€β”€ src/
β”‚   β”œβ”€β”€ config.ts             # Environment-based configuration
β”‚   β”œβ”€β”€ mcp-server.ts         # MCP protocol handler
β”‚   β”œβ”€β”€ zig/
β”‚   β”‚   β”œβ”€β”€ manager.ts        # Multi-version Zig download/cache
β”‚   β”‚   └── executor.ts       # zig ast-check + fmt wrapper
β”‚   β”œβ”€β”€ llm/
β”‚   β”‚   β”œβ”€β”€ model-downloader.ts  # Auto-download GGUF from HuggingFace
β”‚   β”‚   └── session.ts           # node-llama-cpp integration
β”‚   └── tools/
β”‚       β”œβ”€β”€ analyze.ts        # analyze_zig tool (COMPLETE)
β”‚       β”œβ”€β”€ compile.ts        # compile_zig tool (COMPLETE)
β”‚       β”œβ”€β”€ docs.ts           # get_zig_docs tool (COMPLETE)
β”‚       └── suggest.ts        # suggest_fix tool (COMPLETE)
β”œβ”€β”€ scripts/
β”‚   β”œβ”€β”€ train-qwen-standard.py   # Fine-tuning script (COMPLETE)
β”‚   β”œβ”€β”€ scrape-zig-repos.js      # Dataset collection
β”‚   β”œβ”€β”€ install-zig.js           # Zig version installer
β”‚   └── test-config.cjs          # Config system tests
β”œβ”€β”€ data/
β”‚   β”œβ”€β”€ training/             # 13,756 examples (train/val/test)
β”‚   └── zig-docs/             # Scraped documentation
β”œβ”€β”€ models/
β”‚   └── zignet-qwen-7b/       # Fine-tuned model + LoRA adapters
β”œβ”€β”€ tests/
β”‚   β”œβ”€β”€ *.test.ts             # Unit tests (lexer, parser, etc.)
β”‚   └── e2e/
β”‚       β”œβ”€β”€ mcp-integration.test.ts  # 27 E2E tests
β”‚       └── README.md               # Testing guide
β”œβ”€β”€ docs/
β”‚   β”œβ”€β”€ AGENTS.md             # Detailed project spec
β”‚   β”œβ”€β”€ DEVELOPMENT.md        # Development guide
β”‚   └── TESTING.md            # Testing documentation
└── README.md                 # This file

πŸ€– Model Details

Base Model: Qwen/Qwen2.5-Coder-7B-Instruct
Fine-tuning: QLoRA (4-bit) on 13,756 Zig examples
Dataset: 97% real-world repos (Zig 0.13-0.15), 3% documentation
Training: RTX 3090 (24GB VRAM), 3 epochs, ~8 hours
Output: fulgidus/zignet-qwen2.5-coder-7b (HuggingFace)
Quantization: Q4_K_M (~4GB GGUF for node-llama-cpp)

Why Qwen2.5-Coder-7B?

  • Best Zig syntax understanding (benchmarked vs 14 models)

  • Modern idioms (comptime, generics, error handling)

  • Fast inference (~15-20s per query post-quantization)


πŸ“Š Benchmarks

Model

Pass Rate

Avg Time

Quality

Notes

Qwen2.5-Coder-7B

100%

29.58s

⭐⭐⭐⭐⭐

SELECTED - Best idioms

DeepSeek-Coder-6.7B

100%

27.86s

⭐⭐⭐⭐⭐

Didactic, verbose

Llama3.2-3B

100%

12.27s

⭐⭐⭐⭐

Good balance

CodeLlama-7B

100%

24.61s

⭐⭐⭐

Confuses Zig/Rust

Qwen2.5-Coder-0.5B

100%

3.94s

❌

Invents syntax

Full benchmarks: scripts/test-results/


πŸ› οΈ Development

# Run tests
pnpm test

# Run specific component tests
pnpm test -- lexer
pnpm test -- parser
pnpm test -- type-checker

# Watch mode
pnpm test:watch

# Linting
pnpm lint
pnpm lint:fix

# Build
pnpm build

🀝 Contributing

See AGENTS.md for detailed project specification and development phases.

Current needs:

  • Testing on diverse Zig codebases

  • Edge case discovery (parser/type-checker)

  • Performance optimization

  • Documentation improvements


πŸ“„ License

WTFPL v2 β€” Do What The Fuck You Want To Public License



Status: βœ… Phase 4 Complete - Ready for deployment (fine-tuning complete, E2E tests passing)

-
security - not tested
A
license - permissive license
-
quality - not tested

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/fulgidus/zignet'

If you have feedback or need assistance with the MCP directory API, please join our Discord server