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 mai-yyy · MCP Server · ★ 114
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is multi-llm-mcp safe to install? View the security audit →
multi-llm-mcp 一个用于 Claude Code 的 MCP 工具，支持通过 MCP 调用 Codex CLI 执行任务，并支持多个模型（GPT、Kimi、DeepSeek、Qwen 等）并行调用。 本项目基于 FastMCP 开发，主要解决两个问题： 让 Claude Code 可以把任务交给 Codex CLI 执行，例如查看代码、修改文件、重构项目等。 让 Claude Code 可以同时调用多个大模型，从不同模型获得回答，便于对比、补充和交叉参考。 功能特点 Codex CLI 异步任务执行：通过 MCP 工具调用 Codex CLI，并使用 + 的方式等待长任务完成，避免 MCP 客户端单次工具调用超时。 支持 Codex 沙盒模式：、、 三种级别。 单模型会话调用：调用指定模型，并通过 保持多轮上下文。 多模型并行调用：把同一个问题同时发送给多个模型（GPT、Kimi、DeepSeek、Qwen、Claude）。 长任务轮询机制：对耗时较长的 Codex 任务或多模型调用，先返回 ，后续继续通过 工具等待结果。 环境检查工具： 用于检查运行环境、Codex CLI 是否可用、各模型 API Key 是否配置等（不返回任何 key 内容）。 工具列表 环境要求 Python 3.10+ FastMCP OpenAI Python SDK 可选：OpenAI Codex CLI 安装依赖： 如果需要使用 ，还需确保本机已安装 Codex CLI，并能在命令行直接运行： 另外，在用 调度 Codex 之前，确保 Codex CLI 已经登录过账号（首次使用前先在命令行运行 完成登录），否则任务会因为未认证而失败。 模型配置 项目中通过 配置不同模型服务，例如 DeepSeek、Kimi、Qwen、GPT 等。推荐使用环境变量保存模型密钥：
| Stars | 114 |
| Forks | 1 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 63.4659462415786/100 |
| Last Updated | 2026-05-30 |
| Created | 2026-05-29 |
| Platforms | claude-code, cli, codex, mcp, python |
| Est. Tokens | ~1k |
Looking for a multi-llm-mcp alternative? If you're comparing multi-llm-mcp 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.
Unified LLM gateway with weighted load balancing, observability & cost tracking. 统一的 LLM 网关，提供权重负载均衡、可观测性与费用追踪
Bridgic is the next-generation agent development framework for building intelligent systems.
An introduction to the world of AI Agents
Define task-specific AI sub-agents in Markdown for any MCP-compatible tool.
Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTT
MCP-X 是一个**企业级 AI 中台**，集成了 AI 对话、文案生成、视频生成、图片生成、前端应用构建、MCP市场、Agent智能体等多种创作工具，为企业和开发者提供一站式的 AIGC 工作台解决方案。
Explore other popular mcp server tools:
multi-llm-mcp is 一个让 Claude Code 调用 Codex 干活，并可以同时调用多个模型（GPT、Kimi、DeepSeek 等）的 MCP 工具。. It is categorized as a MCP Server with 114 GitHub stars.
multi-llm-mcp is primarily written in Python. It covers topics such as claude-code, codex, codex-cli.
You can find installation instructions and usage details in the multi-llm-mcp GitHub repository at github.com/mai-yyy/multi-llm-mcp. The project has 114 stars and 1 forks, indicating an active community.
multi-llm-mcp is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to multi-llm-mcp on Agent Skills Hub include llmio, bridgic, oreilly-ai-agents. 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: