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 googleapis · MCP Server · ★ 59
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is mcp-toolbox-sdk-go safe to install? View the security audit →
MCP Toolbox SDKs for Go Core Module : TBADK Module : [ server that enables AI assistants like Claude to retrieve and inter
Web app for teams of 20+ members. In-built connections to major LLMs via API. Share chats, prompts, and agents
Authentication, analytics, and prompt visibility for MCP servers with zero code changes. Supports OAuth2.1, DC
A ReAct-Based Highly Robust Autonomous Agent (Harness) Framework.
mcp-use is the framework for MCP with the best DX - Build AI agents, create MCP servers with UI widgets, and
Model Context Protocol (MCP) server for Go using gopls – LSP-powered analysis, tests, coverage, and tooling.
Explore other popular mcp server tools:
mcp-toolbox-sdk-go is Go SDK for interacting with the MCP Toolbox for Databases.. It is categorized as a MCP Server with 59 GitHub stars.
mcp-toolbox-sdk-go is primarily written in Go. It covers topics such as databases, genai-go, genkit-go.
You can find installation instructions and usage details in the mcp-toolbox-sdk-go GitHub repository at github.com/googleapis/mcp-toolbox-sdk-go. The project has 59 stars and 19 forks, indicating an active community.
mcp-toolbox-sdk-go is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to mcp-toolbox-sdk-go on Agent Skills Hub include weather-mcp-server, weam, jetski. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: