mcp-fusion
Allows using the Gemini 2.5 Flash model as a panel model by providing a Google API key. It can be included in the panel to generate responses for analysis.
Allows using GPT-4o as a panel model by providing an OpenAI API key. It can be included in the panel to generate responses for the fusion analysis.
Click on "Deploy 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., "@mcp-fusion analyze the pros and cons of remote work"
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.
MCP Fusion Server
多模型融合分析工具。将问题并行发送给多个 AI 模型,由评审模型综合各方观点,返回结构化分析。
安装
cd mcp-fusion
npm install
npm run buildRelated MCP server: cognition-wheel
在 Claude Code 中配置
在项目 .mcp.json 或全局 ~/.claude/settings.json 中添加:
{
"mcpServers": {
"fusion": {
"command": "node",
"args": ["/Users/thysummer/Desktop/some thing/agent/Claude code/mcp-fusion/dist/index.js"],
"env": {
"ARK_API_KEY": "你的字节方舟CodingPlan key",
"ANTHROPIC_API_KEY": "你的Anthropic key"
}
}
}
}只需要 ARK_API_KEY + ANTHROPIC_API_KEY 就能跑起来(面板走方舟,评审走 Claude)。
如果还想在面板中加入 GPT 或 Gemini,额外配置对应 key 即可。
可用模型
通过 CodingPlan(一个 ARK key):
doubao-seed-2.0-pro— 字节豆包deepseek-v4-pro— DeepSeekdeepseek-v4-flash— DeepSeek 快速版kimi-k2.6— 月之暗面glm-5.1— 智谱minimax-m3— MiniMax
通过各自官方 key:
gpt-4o— OpenAIgemini-2.5-flash— Googleclaude-sonnet— Anthropicclaude-opus— Anthropic
默认配置
面板:
deepseek-v4-pro+kimi-k2.6+glm-5.1评审:
claude-sonnet
自定义使用
调用时可以指定面板和评审模型:
"用 fusion 分析这个问题,面板用 deepseek-v4-pro、gpt-4o、kimi-k2.6,评审用 claude-opus"tool 参数:
query— 要分析的问题panel_models— 可选,面板模型 ID 列表judge_model— 可选,评审模型 ID
Available Tools
1 toolfusionA
Multi-model fusion analysis. Sends the query to multiple AI models in parallel, then a judge model synthesizes their responses into structured analysis (consensus, contradictions, unique insights, blind spots). Use this for complex research questions, multi-perspective analysis, or when accuracy is critical. Available panel models: doubao-seed-2.0-pro, deepseek-v4-pro, deepseek-v4-flash, kimi-k2.6, glm-5.1, minimax-m3, deepseek-v3, deepseek-r1, gpt-4o, gemini-2.5-flash, claude-sonnet, claude-opus. Default panel: deepseek-v4-pro, kimi-k2.6, glm-5.1. Default judge: claude-sonnet.
Inputs: query (required), panel_models, judge_model.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no risk of ambiguity. The tool 'fusion' has a clearly distinct purpose.
With a single tool, naming consistency is not an issue. The tool name 'fusion' is appropriately descriptive.
The server's purpose is multi-model fusion analysis, and a single comprehensive tool is well-suited to this focused scope.
The tool covers all aspects of fusion analysis including consensus, contradictions, unique insights, and blind spots, and offers model selection, leaving no obvious gaps.
Related MCP Connectors
Multi-LLM AI Research & Analysis — smart routing, consensus analysis, due diligence reports
Multi-LLM council: 25+ frontier models in parallel, consensus scoring, verdict-first code review.
Fan out deep research across multiple AI providers, synthesize into one unified report.
Ask GPT, Claude, Gemini and Grok at once: one consensus answer plus where they agree and split.
Related MCP Servers
- AlicenseAqualityDmaintenanceMulti-AI Consensus Tool: Query multiple AI models in parallel, synthesize responses for better accuracy, and reduce AI bias through ensemble decision-making.133MIT
- AlicenseAqualityDmaintenanceEnables querying multiple AI models in parallel (Claude, Gemini, O3) and synthesizing their responses using anonymous analysis to reduce bias, providing a comprehensive answer.119 npm193MIT

polydev-aiofficial
AlicenseNot gradedqualityDmaintenanceQueries multiple AI models simultaneously (GPT 5.2, Claude Opus 4.5, Gemini 3, Grok 4.1) via a single API call to provide diverse expert perspectives and consensus recommendations.MIT- AlicenseNot gradedqualityCmaintenanceEnables querying multiple AI models simultaneously and returns all answers unmerged for the user to weigh.4MIT