by TryCaspian · MCP Server · ★ 871
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
pip install caspian-sdk # the library (import into your code)
git clone https://github.com/TryCaspian/caspian-sdk.gitTaken from the project's README on GitHub. Check the security audit before running it.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 871 |
| Forks | 135 |
| Language | Python |
| Category | MCP Server |
| License | AGPL-3.0 |
| Quality Score | 66/100 |
| Open Issues | 31 |
| Last Updated | 2026-08-25 |
| Created | 2026-07-20 |
| Platforms | mcp, python |
| Est. Tokens | ~18k |
Website · PyPI · npm · llms.txt for agents · Contributing English · 简体中文
These tools work well together with caspian-sdk for enhanced workflows:
Looking for a caspian-sdk alternative? If you're comparing caspian-sdk 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.
Any Agent × Any Provider × Anywhere. Connect Cursor, Claude Code, OpenCode, or Codex to Slack, Telegram, Disco
Email, SMS & phone-call infrastructure for AI agents — send and receive real email and text messages, and plac
🦞 OpenClaw (Clawdbot/Moltbot) 汉化版 - 开源个人 AI 助手中文版 | Claude/ChatGPT LLM 接入 | WhatsApp/Telegram/Discord 多平台 | 每
Agent harness and tookit for building AI agents and agentic applications. CLI and SDKs included
An agent runtime for Python. Give your agent real work. Keep control: every action checked before it runs, eve
Explore the must-have external ready-made toolkits to integrate with your AI agents built with Python and Type
Explore other popular mcp server tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: