zig-mcp

MCP server for Zig that connects AI coding assistants toZLSvia the Language Server Protocol.

Works withClaude Code, Cursor, Windsurf, and any MCP-compatible client.

AI assistant <--(MCP stdio)--> zig-mcp <--(LSP pipes)--> ZLS | zig build / test / check

- Zig0.17.0-dev.1415+64dfaa568 or newer
- ZLS(auto-detected from PATH, or specify with--zls-path)

# 1. Add the marketplace /plugin marketplace add nzrsky/zig-mcp # 2. Install the plugin /plugin install zig-mcp@zig

claude plugin marketplace add nzrsky/zig-mcp && claude plugin install zig-mcp@zig

git clone https://github.com/nzrsky/zig-mcp.git cd zig-mcp zig build -Doptimize=ReleaseFast

# add globally claude mcp add zig-mcp -- /absolute/path/to/zig-mcp --workspace /path/to/your/zig/project # add for current project only claude mcp add --scope project zig-mcp -- /absolute/path/to/zig-mcp --workspace /path/to/your/zig/project

{ "mcpServers": { "zig-mcp": { "command": "/absolute/path/to/zig-mcp", "args": ["--workspace", "/path/to/your/zig/project"] } } }

If you omit--workspace, zig-mcp uses the current working directory.

Add to.cursor/mcp.jsonin your project:

{ "mcpServers": { "zig-mcp": { "command": "/absolute/path/to/zig-mcp", "args": ["--workspace", "/path/to/your/zig/project"] } } }

Add to~/.codeium/windsurf/mcp_config.json:

{ "mcpServers": { "zig-mcp": { "command": "/absolute/path/to/zig-mcp", "args": ["--workspace", "/path/to/your/zig/project"] } } }

--workspace, -w <path> Project root directory (default: cwd) --zls-path <path> Path to ZLS binary (default: auto-detect from PATH) --help, -h Show help --version Show version

All of these answer from ZLS's semantic model — the part a shell and a text search cannot reach.

There is nozig_build,zig_test,zig_format,zig_version,zig_checkorzig_manage. They used to exist and wrappedzig build,zig test,zig fmt,zig version,zig ast-checkandzvm— and a wrapper loses to the shell it wraps: no pipes, no redirection, no working directory of its own. Session transcripts settle it: 526zig buildinvocations through the shell, zero calls to the tool. Run those with your shell.

zig-mcp spawns ZLS as a child process and talks to it over stdin/stdout using the LSP protocol (Content-Length framing). On the other side, it speaks MCP (newline-delimited JSON-RPC) to the AI assistant.

- main-- reads MCP requests, dispatches tool calls, writes responses
- reader-- reads LSP responses from ZLS, correlates by request ID
- stderr-- forwards ZLS stderr to the server log

If ZLS crashes, zig-mcp automatically restarts it and re-opens all tracked documents.

Files are opened in ZLS lazily on first access, and re-synced (didChange) whenever their contents change on disk -- no need to manage document state manually.

# build zig build # run tests (162 unit tests, including a fake-ZLS harness) zig build test # quality gates: lint, coverage, dead code, mutants make lint cov deadcode mutants # run manually echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"capabilities":{}}}' | \ zig-out/bin/zig-mcp --workspace . 2>/dev/null

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

A stateful LSP runtime for AI agents: warm language server sessions with 50+ tools for go-to-definition, find-references, diagnostics, rename, and more across 30+ languages.

MCP server for the Brainfuck programming language that allows your favourite LLM to debug Brainfuck programs.

Diagnoses token waste in Claude Code sessions with 6 anomaly types and severity scoring. Fully local.

MCP server that gives coding agents program-analysis primitives — data flow, call graphs, taint analysis — so they reason from ground truth instead of grep-and-guess. (same as the GitHub About — keeps your messaging consistent across the web).

An MCP service that equips your workspace with a complete set of AI-accessible development tools for reading, editing, executing, and managing code.

Fennara MCP connects AI agents like Codex, Cursor, Claude Code, and Claude Desktop to Godot-aware tools for real Godot projects. It focuses on feedback from Godot: GDScript diagnostics, scene validation, runtime errors, scene inspection, node properties, screenshots, SemanticSearch, and patch-and-rerun workflows.

Search verified engineering fixes by error message or technology. Step-by-step solutions with trust scores, built for developers and AI agents.

LSP-Claw is an MCP server that lets an AI agent safely build, run, and debug Lua/LSP web apps inside a controlled Mako/Xedge/BAS lab, including on embedded or RTOS devices.

Integrates with Language Server Protocol (LSP) to provide features like code completion, diagnostics, and hover information.

Visual Studio extension with 20 Roslyn-powered MCP tools for AI assistants. Semantic code navigation, symbol search, inheritance, call graphs, safe rename, build/test.