Skip to main content
Glama
enesjakozh
ssdeanx

Branch Thinking

by ssdeanx
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Hybrid

Herramienta MCP de pensamiento ramificado

Registro de cambios Asuntos Node.jsMecanografiadoMCPLicencia MIT@dagrejs/graphlibml-kmeanscaché lru@xenova/transformadores@modelcontextprotocol/sdktizaSirenapnpm

Novedades (2025-04):

  • Visualización avanzada: agrupamiento (k-medias/grado), superposiciones de centralidad, agrupamiento de bordes y superposiciones de agentes para tareas y prioridades

  • Caché y precarga de agente: cachés LRU+TTL para incrustaciones, resúmenes, análisis y calentamiento proactivo de caché de agente

  • Análisis mejorado: compatibilidad con focusNode, multirama y en tiempo real; metadatos optimizados para agentes

  • Documentación mejorada e incorporación para agentes y usuarios

Características

  • 🌳 Gestión de sucursales: crear, enfocar y navegar múltiples líneas de pensamiento

  • 🔗 Referencias cruzadas: vincular pensamientos relacionados entre ramas (escritos, puntuados)

  • 💡 AI Insights: generación automática de información y resúmenes

  • Búsqueda semántica: Encuentra pensamientos relacionados usando incrustaciones

  • 📊 Visualización avanzada:

    • Agrupamiento de nodos (k-medias/grado)

    • Superposiciones de centralidad (cercanía, intermediación)

    • Agrupación de bordes

    • Superposiciones de tareas (estado, prioridad, siguiente acción)

    • Superposiciones y metadatos de Agentic para todos los nodos/bordes

    • FocusNode y visualización de múltiples ramas

  • ⚡ Caché y precarga de Agentic:

    • Cachés LRU+TTL para incrustaciones, resúmenes y análisis

    • Calentamiento de caché proactivo para flujos de trabajo de agentes

  • 🗂️ Almacenamiento persistente: consultable, extensible y nunca pierda una idea

  • 🔄 Tiempo real y múltiples ramas: visualice y analice múltiples ramas y nodos en tiempo real

  • 🛠️ Nivel de producción: manejo robusto de errores, optimizaciones de rendimiento y API amigables para agentes y humanos

Related MCP server: Thought Space - MCP Advanced Branch-Thinking Tool

Pila de tecnología

  • Node.js (mayores de 18 años)

  • TypeScript (4.x)

  • @dagrejs/graphlib : Estructura de gráficos, algoritmos y análisis

  • ml-kmeans : Agrupamiento para visualización

  • lru-cache : almacenamiento en caché LRU+TTL para incrustaciones, resúmenes y análisis

  • @xenova/transformers : Canalizaciones de incrustación y resumen

  • @modelcontextprotocol/sdk : Integración del protocolo y agente MCP

  • tiza : estilo de salida CLI

  • Sirena : visualización de Gantt/hoja de ruta

  • pnpm : Gestión rápida de dependencias

Hoja de ruta (Gantt)

gantt
    title Branch-Thinking MCP Roadmap (2025)
    dateFormat  YYYY-MM-DD
    section Q2 2025
    Advanced Visualization/Analytics :done,      vis1, 2025-04-01,2025-04-20
    Agentic Cache & Prefetch         :done,      cache1, 2025-04-10,2025-04-22
    Enhanced Agentic Docs            :done,      doc1, 2025-04-15,2025-04-25
    Real-time Collaboration          :active,    collab1, 2025-04-20,2025-06-01
    Web Visualization Dashboard      :active,    webviz1, 2025-04-25,2025-06-15
    section Q3 2025
    Plugin System                    :planned,   plugin1, 2025-06-15,2025-07-15
    Mobile/Tablet UI                 :planned,   mobile1, 2025-07-01,2025-08-01
    AI Branch Merging                :planned,   merge1, 2025-07-15,2025-08-15
    Knowledge Base Sync              :planned,   sync1, 2025-08-01,2025-09-01

Tabla de contenido

¿Por qué pensar en ramas?

  • Agentic by Design: creado para flujos de trabajo humanos y de IA; cada comando es compatible con el agente.

  • Ramificación real: organice, vincule y razone sobre ideas, código y tareas en paralelo.

  • AI-Native: búsqueda semántica, resumen automático y generación de información lista para usar.

  • Persistente y visual: nunca pierdas una idea: todo es consultable, visualizable y extensible.

Resumen

La herramienta MCP de pensamiento ramificado es una plataforma avanzada de agentes para gestionar, visualizar y razonar sobre ideas, tareas, código y conocimiento ramificados. Permite tanto a agentes de IA como a humanos organizar proyectos complejos, interconectar ideas y automatizar la generación de información mediante un potente paradigma basado en ramas. Con búsqueda semántica, visualización y gestión persistente de tareas y código, está diseñada para flujos de trabajo colaborativos y autónomos de última generación.

La herramienta MCP de pensamiento ramificado es una plataforma avanzada de agentes para gestionar, visualizar y razonar sobre ideas, tareas, código y conocimiento ramificados. Permite tanto a agentes de IA como a humanos organizar proyectos complejos, interconectar ideas y automatizar la generación de información mediante un potente paradigma basado en ramas. Con búsqueda semántica, visualización y gestión persistente de tareas y código, está diseñada para flujos de trabajo colaborativos y autónomos de última generación.

Arquitectura y flujo

flowchart TD
    User([User/Agent 🤖])
    CLI([CLI/API])
    BM[BranchManager 🧠]
    EmbCache[[Embedding/Summary Cache]]
    Storage[(Persistent Storage 💾)]
    Viz([Visualization/Analytics])
    Tasks([Task Extraction])
    Snippets([Code Snippet Storage])

    User-->|Commands/Queries|CLI
    CLI-->|Manage/Query|BM
    BM-->|Cache|EmbCache
    BM-->|Save/Load|Storage
    BM-->|Visualize|Viz
    BM-->|Tasks|Tasks
    BM-->|Snippets|Snippets
    BM-->|Results|CLI
    CLI-->|Output|User

Inicio rápido

Ponte en marcha en segundos:

pnpm install  # Recommended for speed (or npm install)
pnpm build
node dist/index.js --help  # See available commands

Empezando

1. Clonar e instalar

git clone https://github.com/your-org/branch-thinking-mcp.git
cd branch-thinking-mcp
pnpm install  # Or npm install
pnpm build   # Or npm run build

2. Configurar (opcional)

Para la integración de Claude Desktop, agregue a su claude_desktop_config.json :

"branch-thinking": {
  "command": "node",
  "args": [
    "/your-custom-mcp-dir-here/branch-thinking/dist/index.js"
  ]
}

3. Correr

node dist/index.js

Recetas de uso en el mundo real

1. Captura y vinculación de conocimientos

# Batch capture meeting notes
add-thought dev "Discussed semantic search improvements" note
add-thought dev "Agreed to refactor API" decision
# Link related thoughts
link-thoughts t1 t2 supports "API refactor supports search improvements"

2. Extracción de tareas agenéticas

# Extract and manage tasks from a research branch
extract-tasks research
list-tasks research open
update-task-status task-1 in_progress

3. Visualización para obtener información

# Generate and interpret a knowledge graph
visualize dev
# Review AI-generated summary
summarize-branch dev

Ejemplo en vivo: Flujo de trabajo de Agentic

# 1. Create a new branch for your project or idea
create-branch "AI Research"

# 2. Add thoughts and observations
add-thought [branchId] "Explore semantic search for agent workflows" analysis
add-thought [branchId] "Test cross-linking and summarization" observation

# 3. Link related thoughts
link-thoughts [thoughtId1] [thoughtId2] supports "Thought 2 validates Thought 1"

# 4. See your knowledge graph
visualize [branchId]

# 5. Extract tasks and get AI review
extract-tasks [branchId]
review-branch [branchId]

Reemplace [branchId] y [thoughtIdX] con los ID reales de list y history .

Referencia de comandos

Gestión de sucursales

Dominio

Descripción

list

Mostrar todas las sucursales con estado

focus [branchId]

Cambiar el foco a una rama

history [branchId?]

Mostrar historial de pensamiento

summarize-branch [branchId?]

Resumen de IA de la rama

review-branch [branchId?]

Revisión de la rama mediante IA

visualize [branchId?]

Gráfico visual de conexiones

Gestión del pensamiento y la percepción

Dominio

Descripción

insights [branchId?]

Obtenga información generada por IA

crossrefs [branchId?]

Mostrar referencias cruzadas

hub-thoughts [branchId?]

Lista de pensamientos del centro

semantic-search [query]

Encuentra pensamientos similares

link-thoughts [from] [to] [type] [reason?]

Vincular dos pensamientos

add-snippet [content] [tags]

Guardar un fragmento de código

snippet-search [query]

Buscar fragmentos de código

doc-thought [thoughtId]

Documentar un pensamiento

Gestión de tareas

Dominio

Descripción

extract-tasks [branchId?]

Extraer elementos procesables

list-tasks [branchId] [status] [assignee] [due]

Listar/filtrar tareas

update-task-status [taskId] [status]

Actualizar el estado de una tarea

summarize-tasks [branchId]

Resumir tareas

IA y conocimiento

Dominio

Descripción

ask [question]

Respuesta de IA desde la base de conocimientos

Mejores prácticas

  • Comience siempre con create-branch para garantizar un contexto limpio.

  • Utilice list y focus para navegar entre proyectos o líneas de pensamiento.

  • Aproveche summarize-branch y insights después de agregar varias ideas para obtener un contexto generado por IA.

  • Utilice link-thoughts para conectar explícitamente ideas, tareas o códigos para obtener gráficos semánticos más ricos.

  • Después de realizar cambios en el código, ejecute siempre pnpm lint y pnpm build para detectar errores de forma temprana.

  • Descomponer objetivos complejos en secuencias de comandos de pensamiento/tarea/percepción.

  • Iterar y adaptar: utilice los comentarios de los resúmenes, revisiones y visualizaciones para refinar las próximas acciones.

  • Especifique explícitamente los parámetros (branchId, estado, asignado, etc.) para obtener resultados precisos.

  • Utilice referencias cruzadas y enlaces de múltiples saltos para fomentar la creatividad y unir ideas.

  • Indique a los agentes (Claude, GPT-4, etc.) que “piensen paso a paso” o “utilicen la cadena de pensamiento” para obtener mejores resultados.

Seguridad

  • Todos los datos persistentes se almacenan localmente (predeterminado: directorio del proyecto o MCP_STORAGE_PATH )

  • No se permiten llamadas a API externas a menos que se configuren

  • Los agentes/usuarios son responsables de la privacidad de los pensamientos y tareas almacenados.

  • Para informar problemas de seguridad, abra un problema o envíe un correo electrónico al mantenedor.

Solución de problemas y preguntas frecuentes

P: ¡La herramienta no responde! R: Revise los registros del servidor MCP y asegúrese de que la configuración sea correcta.

P: ¿Cómo restablezco el almacenamiento? R: Elimine o mueva el directorio de almacenamiento persistente (ver configuración).

P: ¿Cómo agrego un nuevo comando? R: Extienda handleCommand en src/index.ts y documéntelo en el archivo README.

Accesibilidad e internacionalización

  • Todas las insignias/imágenes tienen texto alternativo descriptivo.

  • El inglés es el idioma predeterminado; se agradecen contribuciones para traducciones.

  • Abra una solicitud de relaciones públicas o un problema si desea ayudar a localizar esta herramienta.

Contribuyendo

¡Agradecemos contribuciones, problemas y solicitudes de funcionalidad! Abra una solicitud de colaboración o un problema en GitHub.

  1. Bifurcar este repositorio

  2. Crea una nueva rama ( git checkout -b feature/your-feature )

  3. Confirme sus cambios

  4. Empujar hacia la rama

  5. Abrir una solicitud de extracción

Referencias y proyectos relacionados

Créditos

  • Concepto y pruebas: @ssdeanx

  • Generación de código central: Claude, GPT-4 y Cascade

  • Implementación, correcciones y documentación: @ssdeanx

Licencia

Instituto Tecnológico de Massachusetts (MIT)

Available Tools

1 tool
branch-thinkingC

Branch-Thinking Tool

Purpose: Use branching commands to create, navigate, and analyze thought branches and tasks.

Usage: Provide a JSON payload with 'type' and relevant parameters in 'args' object. The tool returns an array of items in the format { type: string, text: string }.

Supported Commands:

  • create-branch: { type: 'create-branch', branchId }

  • focus: { type: 'focus', branchId }

  • add-thought: { type: 'add-thought', branchId, content }

  • semantic-search: { type: 'semantic-search', query, topN? }

  • extract-tasks: { type: 'extract-tasks', branchId? }

  • visualize: { type: 'visualize', branchId?, options? }

  • list-branches: { type: 'list-branches' }

  • history: { type: 'history', branchId }

  • insights: { type: 'insights', branchId }

  • crossrefs: { type: 'crossrefs', branchId }

  • hub-thoughts: { type: 'hub-thoughts', branchId }

  • link-thoughts: { type: 'link-thoughts', fromThoughtId, toThoughtId, linkType, reason? }

  • add-snippet: { type: 'add-snippet', content, tags, author? }

  • snippet-search: { type: 'snippet-search', query, topN? }

  • summarize-branch: { type: 'summarize-branch', branchId? }

  • doc-thought: { type: 'doc-thought', thoughtId }

  • review-branch: { type: 'review-branch', branchId? }

  • ask: { type: 'ask', question }

  • summarize-tasks: { type: 'summarize-tasks', branchId? }

  • advance-task: { type: 'advance-task', taskId, status }

  • assign-task: { type: 'assign-task', taskId, assignee }

  • reset-session: { type: 'reset-session' }

  • clear-cache: { type: 'clear-cache' }

  • get-cache-stats: { type: 'get-cache-stats' }

Visualization Options:

  • clustering: { type: 'clustering', algorithm? }

  • centrality: { type: 'centrality', metric? }

  • overlays: { type: 'overlays', features? }

  • analytics: { type: 'analytics', metrics? }

Example Calls and Expected Responses:

// Add a thought
{ "name": "branch-thinking", "args": { "type": "add-thought", "branchId": "research", "content": "Define MCP best practices" } }
// →
[{"type":"text","text":"Thought added to branch research."}]
// Get insights
{ "name": "branch-thinking", "args": { "type": "insights", "branchId": "research" } }
// →
[{"type":"text","text":"Insights for branch research: ['Best practices cluster around workflow safety and semantic search.', 'Cross-references indicate high reuse of planning patterns.']"}]
// Get cross-references
{ "name": "branch-thinking", "args": { "type": "crossrefs", "branchId": "research" } }
// →
[{"type":"text","text":"Cross-references for branch research: [{ from: 't1', to: 't3', type: 'supports', reason: 't1 evidence for t3' }, { from: 't2', to: 't4', type: 'related' }]"}]
// Extract tasks
{ "name": "branch-thinking", "args": { "type": "extract-tasks", "branchId": "research" } }
// →
[{"type":"text","text":"Tasks extracted: [{ id: 'task-123', content: 'Document MCP safety rules', status: 'open' }]"}]
// Summarize tasks
{ "name": "branch-thinking", "args": { "type": "summarize-tasks", "branchId": "research" } }
// →
[{"type":"text","text":"Task summary: 1 open, 2 in progress, 0 closed."}]
// Advance a task
{ "name": "branch-thinking", "args": { "type": "advance-task", "taskId": "task-123", "status": "in_progress" } }
// →
[{"type":"text","text":"Task task-123 status updated to in_progress."}]
// Assign a task
{ "name": "branch-thinking", "args": { "type": "assign-task", "taskId": "task-123", "assignee": "alice" } }
// →
[{"type":"text","text":"Task task-123 assigned to alice."}]
// Semantic search
{ "name": "branch-thinking", "args": { "type": "semantic-search", "query": "workflow planning", "topN": 3 } }
// →
[{"type":"text","text":"Top 3 semantic matches for 'workflow planning' returned."}]
// Link thoughts
{ "name": "branch-thinking", "args": { "type": "link-thoughts", "fromThoughtId": "t1", "toThoughtId": "t2", "linkType": "supports" } }
// →
[{"type":"text","text":"Linked thought t1 to t2 as 'supports'."}]
// Summarize branch
{ "name": "branch-thinking", "args": { "type": "summarize-branch", "branchId": "research" } }
// →
[{"type":"text","text":"Summary for branch research: ..."}]
// Review branch
{ "name": "branch-thinking", "args": { "type": "review-branch", "branchId": "research" } }
// →
[{"type":"text","text":"Branch research reviewed. 2 suggestions found."}]
ParametersJSON Schema
NameRequiredDescriptionDefault
contentNoThought content (string) or batch of thoughts (array of objects).
branchIdNoBranch ID to associate with the thought(s). If omitted, a new branch may be created or the active branch used.
parentBranchIdNoOptional: ID of the parent branch for hierarchical organization.
typeNoThought type: e.g., 'analysis', 'hypothesis', 'observation', 'task', etc. Used for filtering and scoring.
confidenceNoOptional: Confidence score (0-1) for the thought, for ranking or filtering.
keyPointsNoOptional: Key points or highlights extracted from the thought.
relatedInsightsNoOptional: IDs of related insights, for semantic linking.
crossRefsNoOptional: Array of cross-references to other branches, with type, reason, and strength.
commandNoOptional: Navigation or workflow command. Used for agentic/AI interactions.

TDQS

C2.8/5.0
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. While it lists commands and shows example responses, it lacks critical behavioral details: no information about permissions needed, whether operations are destructive, rate limits, error handling, or persistence behavior. The examples show return formats but don't explain system behavior comprehensively.

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

Conciseness3/5

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

The description is well-structured with clear sections (Purpose, Usage, Supported Commands, Visualization Options, Examples). However, it's overly verbose with extensive example calls that could be condensed. The front-loaded purpose is clear, but the length could be optimized for better conciseness.

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

Completeness2/5

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

Given the tool's complexity (9 parameters, nested objects, no output schema, no annotations), the description is incomplete. While it documents commands and shows examples, it lacks crucial context about system behavior, error conditions, authentication requirements, and operational constraints. For such a sophisticated tool with multiple command types, more comprehensive documentation is needed.

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%, providing good documentation of all 9 parameters. The description adds some value by listing specific command types and their parameters in the 'Supported Commands' section, but this largely duplicates what's in the schema's command object. It doesn't provide additional semantic context beyond what the schema already documents well.

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 'to create, navigate, and analyze thought branches and tasks' with specific verbs and resources. However, since there are no sibling tools mentioned, it cannot demonstrate differentiation 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 Guidelines2/5

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

The description provides basic usage instructions ('Provide a JSON payload with type and args') but offers no guidance on when to use specific commands versus alternatives, no context about prerequisites, and no exclusions. It lists commands without explaining their appropriate contexts.

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

B3.2/5.0
Disambiguation5/5

The single tool 'branch-thinking' has no other tools to be confused with, so disambiguation is perfect. All functionality is contained within one tool, eliminating any possibility of misselection between multiple tools.

Naming Consistency5/5

With only one tool named 'branch-thinking', naming consistency is inherently perfect. There are no other tool names to compare against, so no inconsistency can exist in the tool set.

Tool Count2/5

The server has only one tool despite offering extensive functionality (over 20 commands). This is a significant mismatch as the domain suggests a need for multiple specialized tools (e.g., separate tools for branch management, task operations, search, etc.). A single tool forces all operations through one interface, which is inappropriate for the apparent scope.

Completeness5/5

The tool provides comprehensive coverage for thought branching and task management, including creation, navigation, analysis, visualization, task extraction, assignment, and various utility functions. No obvious gaps exist; it supports full lifecycle operations for branches, thoughts, and tasks within its domain.

Maintenance

ActivityInactive
ResponsivenessNo issues

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

Appeared in Searches

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/ssdeanx/branch-thinking-mcp'

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