A
license-
qualityD
maintenanceEnables multiple AI agents to share and read each other's responses to the same prompt, allowing them to reflect on what other LLMs said to the same question.
Last updated
2
MIT
MoA MCP Server
Integrates Xiaomi's MiMo API to use MiMo models (e.g., MiMo V2.5 Pro) as reference agents in a mixture-of-agents discussion, where multiple models analyze a query in parallel and a primary model aggregates the responses to generate a final answer.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MoA MCP Serverdiscuss: pros and cons of electric vehicles"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MoA MCP Server
Mixture-of-Agents MCP Server — 并行调用多个参考模型讨论问题，再由总统筹模型综合输出最佳答案。
架构
你的问题
↓
[DeepSeek V4 Flash] [MiMo V2.5 Pro] ← 参考模型并行分析
↓ ↓
[DeepSeek V4 Pro] ← 总统筹综合输出
↓
最终答案 + 参考意见原文Related MCP server: Red Team MCP
配置
环境变量
变量 | 必填 | 说明 |
| ✅ | DeepSeek API Key |
| ✅ | 小米 MiMo API Key |
| 可选 | 默认 |
| 可选 | 参考模型1，默认 |
| 可选 | 默认 |
| 可选 | 参考模型2，默认 |
| 可选 | 总统筹模型，默认 |
Proma 集成
在 Proma 的 mcp.json 中添加：
{
"moa": {
"command": "node",
"args": ["/path/to/moa-mcp-server/server.js"],
"env": {
"DEEPSEEK_API_KEY": "sk-xxx",
"MIMO_API_KEY": "sk-xxx",
"FLASH_MODEL": "deepseek-chat",
"MIMO_MODEL": "mimo-2.5-pro",
"AGGREGATOR_MODEL": "deepseek-v4-pro"
},
"type": "stdio",
"enabled": true
}
}其他 MCP 客户端
支持任何兼容 MCP 协议的客户端（Claude Desktop、VS Code 等），按对应平台配置 stdio MCP server 即可。
用法
在 Agent 会话中调用 moa_discuss 工具：
query（必填）：需要讨论的问题context（可选）：背景信息
工作原理
将问题并行发送给 DeepSeek V4 Flash 和 MiMo V2.5 Pro
两个参考模型独立分析，返回各自意见
总统筹模型 (DeepSeek V4 Pro) 综合所有参考意见，输出最终答案
返回结果包含最终答案 + 各参考模型的原始意见原文
This server cannot be installed
Maintenance
–Maintainers
–Response time
–Release cycle
–Releases (12mo)
Commit activity
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityDmaintenanceA multi-agent collaboration platform that provides access to over 1,500 models from 68 providers via the Model Context Protocol. It enables users to assemble and coordinate specialized AI teams using advanced orchestration modes like swarm, debate, and hierarchical workflows.Last updated2AGPL 3.0
- AlicenseBqualityCmaintenanceEnables multi-round brainstorming debates between multiple AI models like GPT, DeepSeek, and Ollama to produce synthesized final outputs. Users can orchestrate parallel model interactions where AI agents critique and refine each other's ideas to reach a consolidated conclusion.Last updated38367MIT
- AlicenseAqualityAmaintenanceEnables Claude to chat with various AI models and obtain multi-model consensus for complex decisions.Last updated32312MIT
Related MCP Connectors
Agent-to-agent reasoning-as-a-service: chain-of-thought, analysis, and decision support.
A second opinion for AI agents: one prompt across several live Gonka models + roles, one call.
Create and manage AI agents that collaborate and solve problems through natural language interacti…
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/accoutmissing/moa-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server