No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by danicat · MCP Server · ★ 64
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is godoctor safe to install? View the security audit →
GoDoctor GoDoctor is a Model Context Protocol (MCP) server and CLI extension for Go development. It provides structured tools to help coding agents navigate, edit, build, and test Go codebases safely. User Instructions Installation Antigravity CLI GoDoctor ships as a Gemini CLI-compatible extension. Install using the command (included with Antigravity CLI), then import into : After import, GoDoctor is active in all future sessions. Skills, hooks, and the MCP server are all registered automatically. Gemini CLI (standalone) Claude Code Install the binary globally: Register the MCP server: Append agent instructions to your project: Usage Instructions Once installed, GoDoctor runs automatically in the background of your agent-compatible client. The client agent will discover and call the exposed tools during Go programming tasks. To manually print system instructions for an LLM agent: bash godoc
| Stars | 64 |
| Forks | 7 |
| Language | Go |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 67.0712616241469/100 |
| Last Updated | 2026-08-17 |
| Created | 2025-07-19 |
| Platforms | go |
| Est. Tokens | ~16k |
These tools work well together with godoctor for enhanced workflows:
Explore other popular mcp server tools:
godoctor is A Model Context Protocol server for Go developers. It is categorized as a MCP Server with 64 GitHub stars.
godoctor is primarily written in Go.
You can find installation instructions and usage details in the godoctor GitHub repository at github.com/danicat/godoctor. The project has 64 stars and 7 forks, indicating an active community.
godoctor is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: