by fumingyang2004 · MCP Server · ★ 429
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
git clone https://github.com/fumingyang2004/Tulpa.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 | 429 |
| Forks | 27 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 56/100 |
| Open Issues | 8 |
| Last Updated | 2026-10-23 |
| Created | 2026-09-26 |
| Platforms | claude-code, codex, mcp, python |
| Est. Tokens | ~15k |
Tulpa 在本机查询 QQ / 微信聊天，整理资料、持续调查，并起草符合当前语境的回复。 下载 Windows 版 · 功能清单 · OneBot 配置教程 · 参与开发 Tulpa 是面向 Windows 的个人通信工作台。聊天和资料保存在本机，Agent 在你选择的平台、会话和时间范围内检索，按需读取图片、语音和文件。桌面版解压即用；浏览器入口保留用于开发与测试。 MCP 轻量版：把 QQ / 微信资料接入你正在使用的 Agent。 如果你已经在使用 Codex、Claude Code、DeepSeek Harness、Antigravity 或 WorkBuddy，可以选择 MCP 轻量版。Tulpa 负责导入与实时读取、检索、原文件下载和访问授权，外部 Agent 负责理解、分析与执行任务。轻量版不包含内置 Harness，无需在 Tulpa 中另配模型 API...
Looking for a Tulpa alternative? If you're comparing Tulpa 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.
Delegate tasks to Codex and Gemini directly from within Claude Code.
Define task-specific AI sub-agents in Markdown for any MCP-compatible tool.
Bridge between QQ (SnowLuma OneBot v11) and DeepSeek Harness agents: social simulation, safe MCP tools, slang
The control plane for AI coding agents.
Lightweight Agent Workstation for Codex + Claude code + keke-agent — with dots, task scheduler, git worktree &
Open-source desktop AI agent workspace with one-click Claude Code, Codex, OpenClaw, Hermes Agent setup and cus
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: