mcp-server-go-quality
One MCP server for golangci-lint, govulncheck, and nilaway — a unified Diagnostic\[] array with consistent file:line:column navigation, parallel execution, and zero-config auto-install - for golang development.
README

mcp-server-go-quality
One MCP server for golangci-lint, govulncheck, and nilaway — a unified Diagnostic[] array with consistent file:line:column navigation, parallel execution, and zero-config auto-install.
Demo

What it does
Wraps three Go code quality tools into a single MCP interface. Designed for AI coding agents (Claude Code, Codex, OpenCode, ...) but also useful for CI pipelines and local development. Call one tool (run_code_checks) and get a flat, sorted Diagnostic[] array — all three checkers run in parallel under independent timeouts. Tools auto-install on first use.
| Concern | Raw CLI | This server |
|---|---|---|
| Entry points | 3 separate go install + invocation |
1 MCP tool call |
| Output format | 3 incompatible schemas | 1 unified Diagnostic[] array |
| Tool install | Manual per machine | Auto-install with version pinning |
| Concurrency | Sequential by default | Parallel goroutines, per-tool timeouts |
| Error handling | Parse exit codes and stderr manually | Canonical error field per diagnostic, panic recovery |
| Path normalization | Raw absolute paths | Relative to project root |
| Workspace support | Manual go.work parsing |
Two-pass root discovery (go.work > go.mod) |
Tools bundled
| Tool | Version | Checks |
|---|---|---|
| golangci-lint | v2.11.4 (pinned) | Lint violations, complexity (gocyclo/gocognit), security (gosec) |
| govulncheck | latest | Known CVEs reachable from your code via call-graph analysis |
| nilaway | latest | Inter-procedural nil-panic paths the compiler won't catch |
MCP tools exposed
| Tool | Description |
|---|---|
run_code_checks |
Run all 3 checkers in parallel (or a subset via tools param). Returns sorted Diagnostic[]. |
run_lint |
Run golangci-lint only. |
run_vuln_check |
Run govulncheck only. |
run_nil_check |
Run nilaway only. |
install_tools |
Pre-install all three tools with pinned/latest versions. Call this at session start. |
Output schema
Every tool returns a flat array of this shape, sorted by file then line:
[
{
"tool": "golangci-lint",
"file": "cmd/main.go",
"line": 115,
"column": 1,
"severity": "warning",
"message": "cognitive complexity 18 is high (> 15)",
"error": "",
"native": {"FromLinter": "gocognit", "Text": "...", "SuggestedFixes": [...]}
}
]
| Field | Notes |
|---|---|
severity |
Absent (not "") for govulncheck and nilaway — they have no severity concept |
native |
Full raw tool output. null for error diagnostics that carry no raw context. Govulncheck parse errors carry raw error strings as a JSON array. |
error |
Non-empty on tool failure or panic. Check this first before reading file/line. |
Installation
For AI agents (Claude Code, etc.)
claude mcp add go-quality -- go run github.com/afshinator/mcp-server-go-quality/cmd/mcp-server-go-quality@latest
For other MCP clients, add to your config:
{
"mcpServers": {
"go-quality": {
"command": "mcp-server-go-quality",
"args": []
}
}
}
For humans (local install)
go install github.com/afshinator/mcp-server-go-quality/cmd/mcp-server-go-quality@latest
Then run it directly on a Go project:
cd ~/my-go-project
mcp-server-go-quality
# Or specify a project path and config:
mcp-server-go-quality --config ./my-config.yaml
The server starts in stdio mode — connect any MCP client or test it interactively by piping JSON-RPC. Tools auto-install into $GOBIN on first use.
Prerequisites: Go 1.22+ on PATH.
Agent workflow
- Install tools — call
install_toolsat session start. Returnsinstalled,already_present, andfailedlists. A fast no-op if binaries are at the correct version. - Run checks — call
run_code_checkswithproject_pathset to the project root (or any subdirectory — the server walks up togo.workorgo.mod). - Process diagnostics — check
errorfirst (non-empty = tool failure), then navigate tofile:line:column. Thenativefield carries full raw output for remediation.
Full contract and processing loop: docs/agents/AGENTS.md
Error tables, remediation, and troubleshooting: docs/agents/reference.md
Configuration (.go-quality.yaml)
Place at the project root. All fields optional.
timeout: 5m # per-tool deadline; increase for big monorepos or first vuln DB download
tools:
golangci-lint:
version: v2.11.4
extra_args: []
govulncheck:
version: latest
extra_args: []
nilaway:
version: latest
extra_args: ["--exclude-pkgs=github.com/myorg/vendor"]
Precedence: --config flag > .go-quality.yaml at server CWD > compiled-in defaults.
Go workspace support
Supports single-module go.mod and go.work multi-module workspaces. Pass any subdirectory as project_path — the server walks up to find go.work first, then go.mod. Nilaway automatically collects module paths from use directives and passes them via -include-pkgs.
Contributing
TDD enforced — nearly every source file has a companion _test.go file. Integration tests run against testdata/sample_project/, a small Go module with intentional issues for all three tools.
make test # unit tests (fast)
make test-all # full suite including integration
make lint # golangci-lint
make fmt # gofumpt + goimports
make build # compile the binary
MIT License
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。