Skip to main content
Glama
bartekke8it56w2

Gemini Thinking Server

Protocolo de contexto del modelo - Gemini Thinking Server

Esta es una implementación del Protocolo de Contexto de Modelo (MCP) que se integra con la API Gemini de Google para proporcionar capacidades de pensamiento analítico sin generación de código.

Descripción general

Gemini Thinking Server es un servidor MCP especializado que aprovecha el modelo Gemini de Google para ofrecer pensamiento secuencial y capacidades de resolución de problemas. Permite:

  • Descomponer problemas complejos en pasos

  • Planificación y diseño con espacio para revisión

  • Análisis que podría requerir corrección de rumbo

  • Problemas cuyo alcance total podría no estar claro inicialmente

Related MCP server: gpal

Características

  • Pensamiento impulsado por Géminis : utiliza las capacidades analíticas de Géminis para generar respuestas reflexivas.

  • Metacomentario : proporciona información sobre el proceso de razonamiento.

  • Niveles de confianza : Indica qué tan seguro está Géminis en su análisis.

  • Caminos alternativos : sugiere diferentes enfoques al problema

  • Pensamientos ramificados : permite la exploración de diferentes caminos de pensamiento.

  • Capacidad de revisión : Apoya la revisión de pensamientos previos.

  • Persistencia de sesión : guardar y reanudar sesiones de análisis

Instalación

# Clone the repository
git clone <repository-url>

# Install dependencies
npm install

# Build the project
npm run build

Uso

Configuración del entorno

Antes de ejecutar el servidor, debe configurar su clave API de Gemini:

export GEMINI_API_KEY=your_api_key_here

Ejecución del servidor

node dist/gemini-index.js

Parámetros de la herramienta

La herramienta geminithinking acepta los siguientes parámetros:

  • query (obligatoria): La pregunta o problema a analizar

  • context (opcional): información de contexto adicional

  • approach (opcional): Enfoque sugerido para el problema

  • previousThoughts (opcional): Matriz de pensamientos previos para contexto

  • thought (opcional): Tu paso de pensamiento actual (si está vacío, será generado por Géminis)

  • nextThoughtNeeded (obligatorio): si se necesita otro paso de pensamiento

  • thoughtNumber (obligatorio): Número de pensamiento actual

  • totalThoughts (obligatorio): Estimación del total de pensamientos necesarios

  • isRevision (opcional): si esto revisa el pensamiento previo

  • revisesThought (opcional): ¿Qué pensamiento se está reconsiderando?

  • branchFromThought (opcional): Número de pensamiento del punto de ramificación

  • branchId (opcional): identificador de rama

  • needsMoreThoughts (opcional): Si se necesitan más pensamientos

Gestión de sesiones

La herramienta también admite comandos de gestión de sesiones:

  • sessionCommand : Comando para administrar sesiones ('guardar', 'cargar', 'obtener estado')

  • sessionPath : Ruta para guardar o cargar el archivo de sesión (necesario para los comandos 'guardar' y 'cargar')

Ejemplo: Guardar una sesión

{
  "sessionCommand": "save",
  "sessionPath": "/path/to/save/session.json",
  "query": "dummy",
  "thoughtNumber": 1,
  "totalThoughts": 1,
  "nextThoughtNeeded": false
}

Ejemplo: Cargar una sesión

{
  "sessionCommand": "load",
  "sessionPath": "/path/to/load/session.json",
  "query": "dummy",
  "thoughtNumber": 1,
  "totalThoughts": 1,
  "nextThoughtNeeded": false
}

Ejemplo: Obtener el estado de la sesión

{
  "sessionCommand": "getState",
  "query": "dummy",
  "thoughtNumber": 1,
  "totalThoughts": 1,
  "nextThoughtNeeded": false
}

Ejemplo

A continuación se muestra un ejemplo de cómo utilizar la herramienta:

{
  "query": "How might we design a sustainable urban transportation system?",
  "context": "The city has 500,000 residents and currently relies heavily on personal vehicles.",
  "approach": "Consider environmental, economic, and social factors.",
  "thoughtNumber": 1,
  "totalThoughts": 5,
  "nextThoughtNeeded": true
}

Formato de respuesta

El servidor responde con:

{
  "thought": "The generated thought from Gemini",
  "thoughtNumber": 1,
  "totalThoughts": 5,
  "nextThoughtNeeded": true,
  "branches": [],
  "thoughtHistoryLength": 1,
  "metaComments": "Meta-commentary about the reasoning",
  "confidenceLevel": 0.85,
  "alternativePaths": ["Alternative approach 1", "Alternative approach 2"]
}

Clientes de ejemplo

Se proporcionan varios clientes de ejemplo para demostrar diferentes casos de uso:

  • sample-client.js : Ejemplo básico de cliente

  • example-usage.js : Ejemplo de uso específico

  • codebase-analysis-example.js : Ejemplo de análisis de código base

  • session-example.js : Ejemplo que demuestra la persistencia de la sesión

  • advanced-filtering-example.js : Ejemplo que demuestra el filtrado semántico avanzado

Para ejecutar el ejemplo de sesión:

node dist/session-example.js

Para ejecutar el ejemplo de filtrado avanzado:

node dist/advanced-filtering-example.js

Licencia

Instituto Tecnológico de Massachusetts (MIT)

Available Tools

1 tool
geminithinkingA

A detailed tool for dynamic and reflective problem-solving through Gemini AI. This tool helps analyze problems through a flexible thinking process powered by Google's Gemini model. Each thought can build on, question, or revise previous insights as understanding deepens.

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

Key features:

  • Leverages Gemini AI for deep analytical thinking

  • Provides meta-commentary on the reasoning process

  • Indicates confidence levels for generated thoughts

  • Suggests alternative approaches when relevant

  • 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

  • Session persistence: save and resume your analysis sessions

Parameters explained:

  • query: The question or problem to be analyzed

  • context: Additional context information (e.g., code snippets, background)

  • approach: Suggested approach to the problem (optional)

  • previousThoughts: Array of previous thoughts for context

  • thought: The current thinking step (if empty, will be generated by Gemini)

  • 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

  • metaComments: Meta-commentary from Gemini about its reasoning process

  • confidenceLevel: Gemini's confidence in the generated thought (0-1)

  • alternativePaths: Alternative approaches suggested by Gemini

Session commands:

  • sessionCommand: Command to manage sessions ('save', 'load', 'getState')

  • sessionPath: Path to save or load the session file (required for 'save' and 'load' commands)

You should:

  1. Start with a clear query and any relevant context

  2. Let Gemini generate thoughts by not providing the 'thought' parameter

  3. Review the generated thoughts and meta-commentary

  4. Feel free to revise or branch thoughts as needed

  5. Consider alternative paths suggested by Gemini

  6. Only set next_thought_needed to false when truly done

  7. Use session commands to save your progress and resume later

NameRequiredDescriptionDefault
queryYesThe question or problem to analyze
contextNoAdditional context information
thoughtNoYour current thinking step (if empty, will be generated by Gemini)
approachNoSuggested approach to the problem
branchIdNoBranch identifier
isRevisionNoWhether this revises previous thinking
sessionPathNoPath to save or load the session file
metaCommentsNoMeta-commentary about the reasoning process
thoughtNumberYesCurrent thought number
totalThoughtsYesEstimated total thoughts needed
revisesThoughtNoWhich thought is being reconsidered
sessionCommandNoCommand to manage sessions ('save', 'load', 'getState')
confidenceLevelNoConfidence level in the generated thought (0-1)
alternativePathsNoAlternative approaches suggested
previousThoughtsNoArray of previous thoughts for context
branchFromThoughtNoBranching point thought number
needsMoreThoughtsNoIf more thoughts are needed
nextThoughtNeededYesWhether another thought step is needed

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description fully covers behavioral aspects like meta-commentary, confidence levels, revision, branching, and session persistence. However, it omits potential costs or rate limits associated with the Gemini AI backend, slightly reducing transparency.

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-organized with sections and bullet points, but it is overly verbose. Some redundancy exists between the 'when to use' list and 'key features'. Removing repetition would improve conciseness while retaining clarity.

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

Completeness3/5

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

Given the tool's complexity and lack of output schema, the description adequately explains usage flow and available actions. However, it does not explicitly specify the output structure (e.g., JSON containing generated thought, meta-comments, etc.), leaving minor ambiguity.

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 extra context beyond schema descriptions, e.g., explaining that an empty 'thought' parameter will be AI-generated and that 'thought_number' can exceed initial estimates. This adds meaningful value.

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 is for dynamic, reflective problem-solving via Gemini AI. It includes specific usage scenarios and features. However, with no sibling tools, differentiation is not assessed, but the purpose is clear and distinct from a generic 'think' tool.

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?

The description provides a detailed list of when to use the tool, including breaking down complex problems, planning, and analysis needing course correction. It does not explicitly mention when not to use it, but the extensive positive guidance compensates.

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 updatev1.0.1
    • First observedgeminithinking

TDQS

A4/5.0

Scored across 1 tool

Disambiguation5/5

Only one tool exists, so there is no risk of confusion or overlap with other tools.

Naming Consistency5/5

With a single tool, naming consistency is inherently perfect; the name 'geminithinking' clearly describes its purpose.

Tool Count3/5

The server has only one tool, which feels thin for a domain that could benefit from separate tools for sessions, branching, or analysis management. However, the single tool is feature-rich.

Completeness5/5

The tool covers all expected functionalities for a deep thinking assistant: querying, context, revisions, branching, session persistence, and meta-commentary. No obvious gaps.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Related MCP Connectors

Related MCP Servers

  • A
    license
    A
    quality
    D
    maintenance
    A MCP server that implements sequential thinking protocols, provides structured problem-solving methods, decomposes complex problems into manageable steps, and supports iterative optimization and alternative reasoning paths.
    1
    2
    Apache 2.0
  • A
    license
    A
    quality
    D
    maintenance
    An MCP server that gives your IDE or agent access to Google Gemini with autonomous codebase exploration, enabling deep code analysis, architectural reviews, and bug hunting.
    20
    10
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    An advanced MCP server that provides an agentic interface to Google's Gemini 3.1 models via Vertex AI, combining real-time Google Search, URL analysis, and Python code execution to solve complex multi-step research and data tasks.
    1
    MIT