여러 Claude 인스턴스를 활용하여 향상된 응답을 제공하는 MCP 서버입니다. 동일한 프롬프트를 두 개의 개별 Claude 인스턴스에 전송하고, 세 번째 인스턴스를 사용하여 두 응답에서 가장 적합한 요소를 결합하거나 선택합니다.
다양한 Claude 모델을 지원합니다.
클로드-3-작품-최신
클로드-3-5-소네트-최신
클로드-3-5-하이쿠-최신
클로드-3-하이쿠-20240307
각 AI로부터 단일하고 직접적인 응답을 받습니다.
원본 응답과 출처 표시를 표시합니다.
최적화된 최종 응답을 반환합니다.
Related MCP server: prompte-mcp
저장소를 복제합니다
종속성 설치:
지엑스피1
서버를 빌드하세요:
npm run build서버가 작동하려면 Anthropic API 키가 필요합니다. 환경 변수로 설정하세요.
export ANTHROPIC_API_KEY=your-api-key-here서버는 다음 매개변수를 사용하여 twosplit 이라는 단일 도구를 제공합니다.
prompt (필수): Claude에게 보낼 프롬프트
model (필수): 사용할 Claude 모델(위에 나열된 지원되는 모델 중 하나여야 함)
Claude에서의 도구 사용 예시:
<use_mcp_tool>
<server_name>twosplit</server_name>
<tool_name>twosplit</tool_name>
<arguments>
{
"prompt": "Write a short story about a robot learning to paint",
"model": "claude-3-5-sonnet-latest"
}
</arguments>
</use_mcp_tool>응답에는 다음이 포함됩니다.
최종 최적화된 응답
두 AI의 원래 응답
어떤 부분이 어떤 AI에서 나왔는지 보여주는 출처 표시
서버는 지정된 Claude 모델의 두 개의 별도 인스턴스에 동일한 프롬프트를 보내 단일 직접 응답을 요청합니다.
세 번째 인스턴스는 두 응답과 다음 중 하나를 분석합니다.
하나가 명백히 우수한 경우 단일 최상의 응답을 선택합니다.
두 응답의 가장 좋은 요소를 결합한 새로운 응답을 만듭니다.
최종 응답, 원래 응답 및 출처 귀속은 모두 출력에 포함됩니다.
개발 중에 서버를 감시 모드로 실행하려면:
npm run watch서버의 기능을 검사하려면:
npm run inspectorGet multiple AI perspectives and combine them into the best response
| Name | Required | Description | Default |
|---|---|---|---|
| model | Yes | The Claude model to use (claude-3-opus-latest, claude-3-5-sonnet-latest, claude-3-5-haiku-latest, claude-3-haiku-20240307) | |
| prompt | Yes | The prompt to send to the AI |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions getting 'multiple AI perspectives' and combining them, but doesn't specify how many perspectives, what 'combine' entails (e.g., voting, averaging, synthesis), latency, rate limits, or error handling. For a tool that interacts with AI models, this is a significant gap in transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence: 'Get multiple AI perspectives and combine them into the best response.' It's front-loaded with the core purpose, has zero wasted words, and is appropriately sized for the tool's complexity. Every part of the sentence contributes to understanding the tool's function.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (involving multiple AI calls and combination logic), lack of annotations, and no output schema, the description is insufficient. It doesn't explain the output format, error conditions, or behavioral details like how perspectives are generated or combined. For a tool with no structured support, the description should provide more context to be complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with clear documentation for both parameters ('model' and 'prompt'). The description doesn't add any meaning beyond what the schema provides—it doesn't explain parameter interactions or usage nuances. Given the high schema coverage, a baseline score of 3 is appropriate, as the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Get multiple AI perspectives and combine them into the best response.' It specifies the action ('get' and 'combine') and the resource ('AI perspectives'), making it easy to understand what the tool does. However, since there are no sibling tools, it doesn't need to differentiate from alternatives, so it doesn't reach the highest score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, prerequisites, or specific contexts. It simply states what the tool does without indicating scenarios where it's most appropriate or any limitations. This lack of usage context leaves the agent without direction on optimal application.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0twosplitScored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly defined as getting multiple AI perspectives and combining them, which is distinct and unambiguous in this single-tool context.
Since there is only one tool, naming consistency is inherently perfect. The tool name 'twosplit' follows a single pattern with no deviations or mixing of conventions to evaluate.
A single tool is generally too few for most server purposes, as it limits functionality and flexibility. For a server named 'Twosplit MCP Server' that aims to provide multiple AI perspectives, one tool feels thin and under-scoped, potentially leaving gaps in operations like configuration or result refinement.
The tool surface is severely incomplete for the implied domain of handling AI perspectives. While the 'twosplit' tool covers the core action, there are obvious gaps such as no tools for managing perspectives, adjusting combination parameters, or retrieving historical results, which could lead to agent failures in more complex workflows.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
Augments MCP Server - A comprehensive framework documentation provider for Claude Code
MCP server giving Claude AI access to 22+ NYC public-record databases for real estate due diligence
MCP server for building and testing AI agents with multi-model experimentation and insights.
