Skip to main content
Glama
ThySummer14

mcp-fusion

by ThySummer14
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Remote

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 build

Related 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 — DeepSeek

  • deepseek-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 — OpenAI

  • gemini-2.5-flash — Google

  • claude-sonnet — Anthropic

  • claude-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 tool
fusionA

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.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYesThe question or prompt to analyze with multiple models
panel_modelsNoOptional list of model IDs for the panel. Available: 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
judge_modelNoOptional judge model ID. Available: 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

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden. It fully discloses the parallel execution, judge synthesis, and output structure. It also lists available models and default panel/judge, giving the agent a clear behavioral model of the tool's operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is moderately long but well-structured: first sentence defines core functionality, followed by usage guidance and a clear list of available models. Every sentence adds value, though the model list could be slightly more compact.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 3 parameters (all documented), no siblings, and no output schema, the description covers all needed context: purpose, process, model options, defaults, and use cases. It is fully sufficient for an agent to select and invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds value by specifying default panel_models and judge_model, which are not in the schema. This helps the agent understand optional parameters' typical usage beyond the schema's field descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description begins with 'Multi-model fusion analysis' and clearly states the process: parallel query to multiple models, judge synthesis into structured analysis. It specifies output categories (consensus, contradictions, etc.), making the tool's unique value distinct from single-model tools. No siblings are provided, so distinction isn't needed.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly recommends this tool 'for complex research questions, multi-perspective analysis, or when accuracy is critical.' While it doesn't mention when not to use it or list alternatives, the context of no siblings makes this guidance sufficient for an agent to decide when to invoke.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.7/5.0
Disambiguation5/5

With only one tool, there is no risk of ambiguity. The tool 'fusion' has a clearly distinct purpose.

Naming Consistency5/5

With a single tool, naming consistency is not an issue. The tool name 'fusion' is appropriately descriptive.

Tool Count5/5

The server's purpose is multi-model fusion analysis, and a single comprehensive tool is well-suited to this focused scope.

Completeness5/5

The tool covers all aspects of fusion analysis including consensus, contradictions, unique insights, and blind spots, and offers model selection, leaving no obvious gaps.

Maintenance

ActivityStale
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • cognition-wheel

    Hormold
    A
    license
    A
    quality
    D
    maintenance
    Enables querying multiple AI models in parallel (Claude, Gemini, O3) and synthesizing their responses using anonymous analysis to reduce bias, providing a comprehensive answer.
    1
    49
    193
    MIT

  • fusion-mcp

    yksanjo
    A
    license
    A
    quality
    C
    maintenance
    Enables MCP clients to call OpenRouter Fusion, which queries a panel of models in parallel and synthesizes a single answer using a judge model, useful for research and critical decisions.
    1
    MIT
  • polydev-ai by polydev-ai

    polydev-aiofficial

    polydev-ai
    A
    license
    Not graded
    quality
    D
    maintenance
    Queries 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

Latest Blog Posts

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/ThySummer14/mcp-fusion'

If you have feedback or need assistance with the MCP directory API, please join our Discord server