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 kontext-security · MCP Server · ★ 210
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is kontext-cli safe to install? View the security audit →
Website | Documentation | Dashboard | Discord Kontext is an authorization platform for AI agents. It helps teams control what agents can access and do with scoped credentials, policy enforcement, approvals, and audit trails. Kontext can run local-first for developer agents and extend to managed or self-hosted deployments for security-sensitive environments. 🚀 Quickstart Start a local protected session This starts the currently supported adapter, Claude Code, with a local Kontext runtime. No hosted login is required. By default, Kontext runs in observe mode: the agent keeps running, while Kontext records , , and
| Stars | 210 |
| Forks | 8 |
| Language | Go |
| Category | MCP Server |
| License | MIT |
| Quality Score | 69.0083161943468/100 |
| Open Issues | 15 |
| Last Updated | 2026-08-14 |
| Created | 2026-04-05 |
| Platforms | cli, go, mcp |
| Est. Tokens | ~16k |
These tools work well together with kontext-cli for enhanced workflows:
Looking for a kontext-cli alternative? If you're comparing kontext-cli with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Supercharge AI Agents, Safely
Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.
Open-source Agentic AI framework in Go for building, orchestrating, and deploying intelligent agents. LLM-agno
Zero-knowledge credentials infrastructure built for AI agents to operate, not just consume.
A unified CLI for discovering and invoking tools across OpenAPI, MCP, GraphQL, gRPC, and JSON-RPC
Local-first AI knowledge layer. Extract architecture, query from any AI tool via MCP. Private by architecture.
Explore other popular mcp server tools:
kontext-cli is Runtime Security for tool-using AI agents, with local policies, pre-action enforcement, and forensic audit trails.. It is categorized as a MCP Server with 210 GitHub stars.
kontext-cli is primarily written in Go. It covers topics such as ai, ai-agents, audit-logging.
You can find installation instructions and usage details in the kontext-cli GitHub repository at github.com/kontext-security/kontext-cli. The project has 210 stars and 8 forks, indicating an active community.
kontext-cli is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to kontext-cli on Agent Skills Hub include mcpproxy-go, agent-deck, AgenticGoKit. 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: