Skip to main content
Glama
zxkane

Amazon Bedrock MCP Server

by zxkane

Servidor MCP de Amazon Bedrock

Un servidor de Protocolo de control de modelos (MCP) que se integra con el modelo Nova Canvas de Amazon Bedrock para la generación de imágenes de IA.

Características

  • Generación de imágenes de alta calidad a partir de descripciones de texto utilizando el modelo Nova Canvas de Amazon

  • Control avanzado mediante indicaciones negativas para refinar la composición de la imagen

  • Opciones de configuración flexibles para las dimensiones y la calidad de la imagen

  • Generación de imágenes deterministas con control de semillas

  • Validación de entrada robusta y manejo de errores

Related MCP server: AWS Nova Canvas

Prerrequisitos

  1. Cuenta activa de AWS con acceso al modelo Amazon Bedrock y Nova Canvas

  2. Credenciales de AWS configuradas correctamente con los permisos necesarios

  3. Node.js versión 18 o posterior

Instalación

Configuración de credenciales de AWS

El servidor requiere credenciales de AWS con los permisos adecuados de Amazon Bedrock. Configúrelas mediante uno de los siguientes métodos:

  1. Variables de entorno:

    export AWS_ACCESS_KEY_ID=your_access_key
    export AWS_SECRET_ACCESS_KEY=your_secret_key
    export AWS_REGION=us-east-1  # or your preferred region
  2. Archivo de credenciales de AWS ( ~/.aws/credentials ):

    [the_profile_name]
    aws_access_key_id = your_access_key
    aws_secret_access_key = your_secret_key

    Variable de entorno para el perfil activo:

    export AWS_PROFILE=the_profile_name
  3. Rol de IAM (cuando se implementa en la infraestructura de AWS)

Integración de escritorio de Claude

Para integrarse con Claude Desktop, agregue la siguiente configuración a su archivo de configuración:

MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "amazon-bedrock": {
      "command": "npx",
      "args": [
        "-y",
        "@zxkane/mcp-server-amazon-bedrock"
      ],
      "env": {
        "AWS_PROFILE": "your_profile_name",         // Optional, only if you want to use a specific profile
        "AWS_ACCESS_KEY_ID": "your_access_key",     // Optional if using AWS credentials file or IAM role
        "AWS_SECRET_ACCESS_KEY": "your_secret_key", // Optional if using AWS credentials file or IAM role
        "AWS_REGION": "us-east-1"                   // Optional, defaults to 'us-east-1'
      }
    }
  }
}

Herramientas disponibles

generar_imagen

Crea imágenes a partir de descripciones de texto utilizando el modelo Nova Canvas de Amazon Bedrock.

Parámetros

  • prompt (obligatoria): Texto descriptivo de la imagen deseada (1-1024 caracteres)

  • negativePrompt (opcional): Elementos a excluir de la imagen (1-1024 caracteres)

  • width (opcional): Ancho de la imagen en píxeles (predeterminado: 1024)

  • height (opcional): altura de la imagen en píxeles (predeterminado: 1024)

  • quality (opcional): Nivel de calidad de imagen: "estándar" o "premium" (predeterminado: "estándar")

  • cfg_scale (opcional): Intensidad de adherencia rápida (1,1-10, valor predeterminado: 6,5)

  • seed (opcional): Semilla de generación para reproducibilidad (0-858993459, predeterminado: 12)

  • numberOfImages (opcional): tamaño del lote para la generación (1-5, predeterminado: 1)

Ejemplo de implementación

const result = await callTool('generate_image', {
  prompt: "A serene mountain landscape at sunset",
  negativePrompt: "people, buildings, vehicles",
  quality: "premium",
  cfg_scale: 8,
  numberOfImages: 2
});

Pautas de indicaciones

Para obtener resultados óptimos, evite usar frases negativas ("no", "no", "sin") en la solicitud principal. En su lugar, mueva estos elementos al parámetro negativePrompt ". Por ejemplo, en lugar de usar "un paisaje sin edificios" en la solicitud, use "edificios" en " negativePrompt ".

Para obtener instrucciones de uso detalladas, consulte la documentación de Nova Canvas .

Desarrollo

Para configurar y ejecutar el servidor en un entorno local:

git clone https://github.com/zxkane/mcp-server-amazon-bedrock.git
cd mcp-server-amazon-bedrock
npm install
npm run build

Consideraciones de rendimiento

El tiempo de generación se ve afectado por la resolución ( width y height ), numberOfImages y la configuración quality . Al usar valores más altos, tenga en cuenta las posibles implicaciones de tiempo de espera en su implementación.

Licencia

Este proyecto está licenciado bajo la licencia MIT: consulte el archivo de LICENCIA para obtener más detalles.

Available Tools

1 tool
generate_imageC

Generate image(s) using Amazon Nova Canvas model. The returned data is Base64-encoded string that represent each image that was generated.

ParametersJSON Schema
NameRequiredDescriptionDefault
cfg_scaleNoHow closely to follow the prompt (1.1-10, default: 6.5)
heightNoHeight of the generated image (default: 1024)
negativePromptNoOptional text description of what to avoid in the image (1-1024 characters)
numberOfImagesNoNumber of images to generate (1-5, default: 1)
promptYesText description of the image to generate (1-1024 characters)
qualityNoQuality of the generated image (default: standard)
seedNoSeed for reproducible generation (0-858993459, default: 12)
widthNoWidth of the generated image (default: 1024)

TDQS

C2.9/5.0
Behavior2/5

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 mentions the return format (Base64-encoded string) but lacks critical details such as rate limits, authentication requirements, error handling, or whether this is a read/write operation. For a complex image generation tool, this is insufficient.

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 concise and front-loaded, consisting of two clear sentences. However, it could be slightly more efficient by combining ideas, but it avoids unnecessary verbosity.

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 complexity of an image generation tool with 8 parameters and no output schema or annotations, the description is incomplete. It covers the basic purpose and return format but misses behavioral context, usage guidelines, and output details, leaving significant gaps for an AI agent.

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 fully documents all 8 parameters. The description adds no parameter-specific information beyond what's in the schema, resulting in a baseline score of 3.

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: 'Generate image(s) using Amazon Nova Canvas model.' It specifies the verb ('generate') and resource ('image(s)'), and identifies the specific model. However, without sibling tools, we cannot assess differentiation, so it cannot achieve a perfect 5.

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 no guidance on when to use this tool versus alternatives, prerequisites, or typical use cases. It simply states what the tool does without context for selection.

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 observedgenerate_image

TDQS

B3/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of confusion or overlap between tools. The tool 'generate_image' has a clear and distinct purpose that cannot be mistaken for any other tool in the set.

Naming Consistency5/5

The single tool name 'generate_image' follows a verb_noun pattern, and with only one tool, consistency is inherently perfect. There are no other tools to compare against, so no inconsistencies can arise.

Tool Count2/5

A single tool is too few for a server named 'Amazon Bedrock MCP Server', which suggests a broader scope related to Amazon Bedrock services. This minimal toolset feels thin and incomplete for the implied domain, limiting functionality to just image generation.

Completeness1/5

The tool surface is severely incomplete for the server's purpose. Amazon Bedrock includes multiple models and capabilities beyond image generation, such as text generation, embeddings, and model management. The single tool fails to cover these core aspects, leaving significant gaps that will cause agent failures.

Maintenance

ActivityInactive
ResponsivenessNo issues

Related MCP Connectors

Related MCP Servers