Skip to main content
Glama
xinzhongyouhai

MCP Sequential Thinking Tools

mcp-순차적 사고-도구

문제 해결 도구 사용을 안내하도록 설계된MCP 순차적 사고 서버(MCP Sequential Thinking Server) 를 기반으로 개발되었습니다. 이 서버는 복잡한 문제를 관리 가능한 단계로 세분화하고 각 단계에서 가장 효과적인 MCP 도구에 대한 권장 사항을 제공합니다.

순차적 사고와 지능형 도구 제안을 결합하는 모델 컨텍스트 프로토콜(MCP) 서버입니다. 문제 해결 과정의 각 단계에 대해 신뢰도 점수에 따라 사용할 도구에 대한 권장 사항과 각 도구가 적합한 이유에 대한 근거를 제공합니다.

특징

  • 🤔 순차적 사고를 통한 역동적이고 성찰적인 문제 해결

  • 🔄 적응하고 진화하는 유연한 사고 과정

  • 🌳 생각의 분기화 및 수정 지원

  • 🛠️ 각 단계에 맞는 지능형 도구 추천

  • 📊 도구 제안에 대한 신뢰도 평가

  • 🔍 도구 권장 사항에 대한 자세한 근거

  • 📝 예상 결과를 통한 단계 추적

  • 🔄 이전 단계와 남은 단계를 통한 진행 상황 모니터링

  • 🎯 각 단계에 대한 대체 도구 제안

Related MCP server: Clear Thought Server

작동 원리

이 서버는 사고 과정의 각 단계를 분석하고 작업 완료에 도움이 되는 적절한 MCP 도구를 추천합니다. 각 권장 사항은 다음과 같습니다.

  • 도구가 현재 요구 사항과 얼마나 잘 일치하는지 나타내는 신뢰도 점수(0-1)

  • 해당 도구가 도움이 될 이유를 명확하게 설명하세요.

  • 도구 실행 순서를 제안하는 우선 순위 수준

  • 또한 사용될 수 있는 대체 도구

이 서버는 사용자 환경에서 사용 가능한 모든 MCP 도구와 호환됩니다. 현재 단계의 요구 사항에 따라 권장 사항을 제공하지만, 실제 도구 실행은 소비자(예: Claude)가 담당합니다.

사용 예

다음은 서버가 도구 사용을 안내하는 방법의 예입니다.

지엑스피1

서버는 진행 상황을 추적하고 다음을 지원합니다.

  • 다양한 접근 방식을 탐색하기 위한 브랜치 생성

  • 새로운 정보로 이전 생각 수정하기

  • 여러 단계에 걸쳐 컨텍스트 유지

  • 현재 결과를 바탕으로 다음 단계 제안

구성

이 서버를 사용하려면 MCP 클라이언트를 통한 구성이 필요합니다. 다음은 다양한 환경에 대한 예시입니다.

클라인 구성

Cline MCP 설정에 다음을 추가하세요.

{
	"mcpServers": {
		"mcp-sequentialthinking-tools": {
			"command": "npx",
			"args": ["-y", "mcp-sequentialthinking-tools"]
		}
	}
}

WSL 구성을 사용한 Claude Desktop

WSL 환경의 경우 Claude Desktop 구성에 다음을 추가하세요.

{
	"mcpServers": {
		"mcp-sequentialthinking-tools": {
			"command": "wsl.exe",
			"args": [
				"bash",
				"-c",
				"source ~/.nvm/nvm.sh && /home/username/.nvm/versions/node/v20.12.1/bin/npx mcp-sequentialthinking-tools"
			]
		}
	}
}

API

서버는 구성 가능한 매개변수를 사용하여 단일 MCP 도구를 구현합니다.

순차적 사고 도구

사고를 통해 역동적이고 사려 깊은 문제 해결을 위한 도구로, 지능적인 도구 추천을 제공합니다.

매개변수:

  • thought (문자열, 필수): 현재 생각 단계

  • next_thought_needed (부울, 필수): 다른 생각 단계가 필요한지 여부

  • thought_number (정수, 필수): 현재 생각 번호

  • total_thoughts (정수, 필수): 필요한 총 생각 수 추정

  • is_revision (부울, 선택 사항): 이것이 이전 생각을 수정하는지 여부

  • revises_thought (정수, 선택 사항): 어떤 생각이 재고되고 있는가

  • branch_from_thought (정수, 선택 사항): 분기점 생각 번호

  • branch_id (문자열, 선택 사항): 지점 식별자

  • needs_more_thoughts (부울, 선택 사항): 더 많은 생각이 필요한 경우

  • current_step (객체, 선택 사항): 다음을 포함한 현재 단계 권장 사항:

    • step_description : 무엇을 해야 하는가

    • recommended_tools : 신뢰도 점수가 포함된 도구 추천 배열

    • expected_outcome : 이 단계에서 무엇을 기대할 수 있을까요?

    • next_step_conditions : 다음 단계의 조건

  • previous_steps (배열, 선택 사항): 이미 권장된 단계

  • remaining_steps (배열, 선택 사항): 예정된 단계에 대한 간략한 설명

개발

설정

  1. 저장소를 복제합니다

  2. 종속성 설치:

pnpm install
  1. 프로젝트를 빌드하세요:

pnpm build
  1. 개발 모드에서 실행:

pnpm dev

출판

이 프로젝트에서는 버전 관리를 위해 변경 세트를 사용합니다. 게시하려면 다음을 수행하세요.

  1. 변경 세트를 만듭니다.

pnpm changeset
  1. 패키지 버전:

pnpm changeset version
  1. npm에 게시:

pnpm release

기여하다

기여를 환영합니다! 풀 리퀘스트를 제출해 주세요.

특허

MIT 라이센스 - 자세한 내용은 LICENSE 파일을 참조하세요.

감사의 말

Available Tools

1 tool
sequentialthinking_toolsA

A detailed tool for dynamic and reflective problem-solving through thoughts. This tool helps analyze problems through a flexible thinking process that can adapt and evolve. Each thought can build on, question, or revise previous insights as understanding deepens.

IMPORTANT: When initializing this tool, you must pass all available tools that you want the sequential thinking process to be able to use. The tool will analyze these tools and provide recommendations for their use.

When to use this tool:

  • Breaking down complex problems into steps

  • Planning and design with room for revision

  • Analysis that might need course correction

  • Problems where the full scope might not be clear initially

  • Problems that require a multi-step solution

  • Tasks that need to maintain context over multiple steps

  • Situations where irrelevant information needs to be filtered out

  • When you need guidance on which tools to use and in what order

Key features:

  • You can adjust total_thoughts up or down as you progress

  • You can question or revise previous thoughts

  • You can add more thoughts even after reaching what seemed like the end

  • You can express uncertainty and explore alternative approaches

  • Not every thought needs to build linearly - you can branch or backtrack

  • Generates a solution hypothesis

  • Verifies the hypothesis based on the Chain of Thought steps

  • Recommends appropriate tools for each step

  • Provides rationale for tool recommendations

  • Suggests tool execution order and parameters

  • Tracks previous recommendations and remaining steps

Parameters explained:

  • thought: Your current thinking step, which can include:

  • Regular analytical steps

  • Revisions of previous thoughts

  • Questions about previous decisions

  • Realizations about needing more analysis

  • Changes in approach

  • Hypothesis generation

  • Hypothesis verification

  • Tool recommendations and rationale

  • next_thought_needed: True if you need more thinking, even if at what seemed like the end

  • thought_number: Current number in sequence (can go beyond initial total if needed)

  • total_thoughts: Current estimate of thoughts needed (can be adjusted up/down)

  • is_revision: A boolean indicating if this thought revises previous thinking

  • revises_thought: If is_revision is true, which thought number is being reconsidered

  • branch_from_thought: If branching, which thought number is the branching point

  • branch_id: Identifier for the current branch (if any)

  • needs_more_thoughts: If reaching end but realizing more thoughts needed

  • current_step: Current step recommendation, including:

  • step_description: What needs to be done

  • recommended_tools: Tools recommended for this step

  • expected_outcome: What to expect from this step

  • next_step_conditions: Conditions to consider for the next step

  • previous_steps: Steps already recommended

  • remaining_steps: High-level descriptions of upcoming steps

You should:

  1. Start with an initial estimate of needed thoughts, but be ready to adjust

  2. Feel free to question or revise previous thoughts

  3. Don't hesitate to add more thoughts if needed, even at the "end"

  4. Express uncertainty when present

  5. Mark thoughts that revise previous thinking or branch into new paths

  6. Ignore information that is irrelevant to the current step

  7. Generate a solution hypothesis when appropriate

  8. Verify the hypothesis based on the Chain of Thought steps

  9. Consider available tools that could help with the current step

  10. Provide clear rationale for tool recommendations

  11. Suggest specific tool parameters when appropriate

  12. Consider alternative tools for each step

  13. Track progress through the recommended steps

  14. Provide a single, ideally correct answer as the final output

  15. Only set next_thought_needed to false when truly done and a satisfactory answer is reached

ParametersJSON Schema
NameRequiredDescriptionDefault
branch_from_thoughtNoBranching point thought number
branch_idNoBranch identifier
current_stepNoCurrent step recommendation
is_revisionNoWhether this revises previous thinking
needs_more_thoughtsNoIf more thoughts are needed
next_thought_neededYesWhether another thought step is needed
previous_stepsNoSteps already recommended
remaining_stepsNoHigh-level descriptions of upcoming steps
revises_thoughtNoWhich thought is being reconsidered
thoughtYesYour current thinking step
thought_numberYesCurrent thought number
total_thoughtsYesEstimated total thoughts needed

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behavioral traits such as adaptability ('adjust total_thoughts up or down'), revision capabilities ('question or revise previous thoughts'), and process flow ('Generates a solution hypothesis,' 'Verifies the hypothesis'), though it lacks details on error handling or performance limits.

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

Conciseness2/5

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

The description is excessively long and repetitive, with multiple sections (e.g., 'Key features,' 'Parameters explained,' 'You should') that overlap in content. It includes unnecessary verbosity, such as listing 15 'You should' items, which reduces clarity and efficiency without adding proportional value.

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

Completeness4/5

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

Given the tool's high complexity (12 parameters, nested objects) and no annotations or output schema, the description does a good job covering the tool's purpose, usage, and behavioral aspects. However, it lacks details on output format or error conditions, which are important for such a sophisticated tool, preventing a perfect score.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds some value by explaining the 'thought' parameter with examples (e.g., 'Regular analytical steps,' 'Hypothesis generation') and listing other parameters, but this largely repeats schema information, resulting in a baseline score.

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

Purpose4/5

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

The description clearly states the tool's purpose as 'dynamic and reflective problem-solving through thoughts' and 'analyze problems through a flexible thinking process,' which is specific and actionable. However, with no sibling tools provided, it cannot differentiate from alternatives, preventing a perfect score.

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

Usage Guidelines5/5

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

The description includes an explicit 'When to use this tool' section with 8 specific scenarios (e.g., 'Breaking down complex problems into steps,' 'Planning and design with room for revision'), providing clear guidance on when to apply this tool. No alternatives are mentioned due to no siblings, but the context is comprehensive.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev1.0.0
    • First observedsequentialthinking_tools

TDQS

A3.8/5.0

Scored across 1 tool

Disambiguation5/5

There is only one tool, so there is no ambiguity or overlap with other tools. The tool has a clearly defined and distinct purpose focused on sequential thinking and problem-solving.

Naming Consistency5/5

With only one tool, naming consistency is inherently perfect. The tool name 'sequentialthinking_tools' uses snake_case, which is consistent within itself, and there are no other tools to cause inconsistency.

Tool Count2/5

The server is named 'MCP Sequential Thinking Tools' and has only one tool, which suggests a thin or incomplete surface. For a domain focused on dynamic problem-solving and tool orchestration, a single tool may not adequately cover the expected scope, such as separate tools for planning, analysis, or verification steps.

Completeness2/5

The tool aims to handle complex problem-solving, planning, and tool recommendations, but as a single tool, it likely consolidates multiple functionalities into one interface. This can lead to gaps in modularity and clarity, as agents might expect separate tools for distinct phases like hypothesis generation, verification, or step tracking, rather than a monolithic solution.

Maintenance

ActivityInactive
ResponsivenessNo issues

Related MCP Connectors

Related MCP Servers

  • A
    license
    A
    quality
    A
    maintenance
    An adaptation of the MCP Sequential Thinking Server designed to guide tool usage in problem-solving. This server helps break down complex problems into manageable steps and provides recommendations for which MCP tools would be most effective at each stage.
    1
    476 npm
    587
    MIT
  • F
    license
    C
    quality
    D
    maintenance
    Provide systematic thinking, mental models, and debugging approaches to enhance problem-solving capabilities. Enable structured reasoning and decision-making support for complex problems. Facilitate integration with MCP-compatible clients for advanced cognitive workflows.
    11
    5
    -
  • A
    license
    Not graded
    quality
    D
    maintenance
    A sequential thinking tool based on the MCP protocol, used to break down complex problems into manageable steps and provide intelligent tool recommendations for each step.
    2
    Apache 2.0