by omaekumiko2-create · MCP Server · ★ 126
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Local-first MCP password and credential manager for AI agents. Use passwords, API keys, SSH identities, and TOTP without exposing hidden plaintext to the model.
| Stars | 126 |
| Forks | 5 |
| Language | Rust |
| Category | MCP Server |
| License | MIT |
| Quality Score | 57.1198901604346/100 |
| Last Updated | 2026-08-30 |
| Created | 2026-08-24 |
| Platforms | claude-code, codex, mcp, rust |
| Est. Tokens | ~22k |
These tools work well together with kru for enhanced workflows:
Looking for a kru alternative? If you're comparing kru 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.
Cognitive Deterministic Memory Security OS for Agentic AI. Deterministic root-cause retrieval that reaches bac
Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTT
AI-powered E2E testing for 10 platforms. 253 MCP tools. Zero config. Works with Claude, Cursor, Windsurf, Copi
Persistent memory for AI coding agents
MCP Fusion - The framework for AI-native MCP servers.
Credential gateway for AI agents. Log in once via Oauth2 or API Key. Every agent stays authenticated — headles
Explore other popular mcp server tools:
kru is Local-first MCP password and credential manager for AI agents. Use passwords, API keys, SSH identities, and TOTP without exposing hidden plaintext to the model.. It is categorized as a MCP Server with 126 GitHub stars.
kru is primarily written in Rust. It covers topics such as ai-agents, ai-security, api-key-management.
You can find installation instructions and usage details in the kru GitHub repository at github.com/omaekumiko2-create/kru. The project has 126 stars and 5 forks, indicating an active community.
kru is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to kru on Agent Skills Hub include vestige, deterministic-agent-control-protocol, flutter-skill. 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: