mcp/aws-bedrock-data-automation-mcp-server pulls statistics

AWS Bedrock Data Automation MCP Server

Analyze documents, images, videos, and audio.

What is an MCP Server?

MCP Info

Attribute	Details
Docker Image	mcp/aws-bedrock-data-automation-mcp-server
Author	awslabs
Repository	https://github.com/awslabs/mcp

Image Building Info

Attribute	Details
Dockerfile	https://github.com/awslabs/mcp/blob/780e3f1d57c77f9c0b88279711c5b95e23cfb91d/src/aws-bedrock-data-automation-mcp-server/Dockerfile
Commit	780e3f1d57c77f9c0b88279711c5b95e23cfb91d
Docker Image built by	Docker Inc.
Docker Scout Health Score
Verify Signature	COSIGN_REPOSITORY=mcp/signatures cosign verify mcp/aws-bedrock-data-automation-mcp-server --key https://raw.githubusercontent.com/docker/keyring/refs/heads/main/public/mcp/latest.pub
Licence	Apache License 2.0

Available Tools (3)

Tools provided by this Server	Short Description
analyzeasset	[DEPRECATED] Analyze an asset using a data automation project.
getprojectdetails	[DEPRECATED] Get details of a data automation project.
getprojects	[DEPRECATED] Get a list of data automation projects.

---

Tools Details

Tool: analyzeasset

[DEPRECATED] Analyze an asset using a data automation project.

This tool extracts insights from unstructured content (documents, images, videos, audio) using Amazon Bedrock Data Automation.

Usage

Use this tool to analyze various types of assets (documents, images, videos, audio files) using a data automation project. You can specify a particular project to use for analysis or let the system use a default public project if none is provided.

Supported Asset Types

• Documents: PDF, DOCX, TXT, etc.
• Images: JPG, PNG, etc.
• Videos: MP4, MOV, etc.
• Audio: MP3, WAV, etc.

Examples

# Analyze a document using the default public project
results = await analyzeasset(assetPath='/path/to/document.pdf')

# Analyze an image using a specific project
results = await analyzeasset(
    assetPath='/path/to/image.jpg',
    projectArn='arn:aws:bedrock:us-west-2:123456789012:data-automation-project/my-project',
)

Output Format

The output is a dictionary containing the analysis results, which vary based on:

• The type of asset being analyzed
• The capabilities of the data automation project used
• The specific insights extracted (text, entities, sentiment, etc.) Parameters|Type|Description -|-|- assetPath|string|The path to the asset projectArn|string optional|The ARN of the project. Uses default public project if not provided

---

Tool: getprojectdetails

[DEPRECATED] Get details of a data automation project.

Usage

Use this tool to retrieve detailed information about a specific data automation project after you've identified its ARN using the getprojects tool.

Example

# Get details for a specific project
project_details = await getprojectdetails(
    projectArn='arn:aws:bedrock:us-west-2:123456789012:data-automation-project/my-project'
)

Output Format

The output is a dictionary containing comprehensive project details including:

• Basic project information (name, ARN, stage)
• Configuration settings
• Input/output specifications
• Associated blueprints
• Creation and modification timestamps Parameters|Type|Description -|-|- projectArn|string|The ARN of the project

---

Tool: getprojects

[DEPRECATED] Get a list of data automation projects.

Usage

Use this tool to retrieve a list of all available data automation projects in your account. This is typically the first step when working with data automation to discover what projects are available for use.

Example

# Get all available data automation projects
projects = await getprojects()

Output Format

The output is a dictionary containing:

• projects: A list of project objects, each with:
  • projectArn: The Amazon Resource Name (ARN) of the project
  • projectName: The name of the project
  • projectStage: The stage of the project (e.g., DRAFT, PUBLISHED)
  • creationTime: When the project was created
  • lastModifiedTime: When the project was last modified

Returns: A dict containing a list of data automation projects.

Use this MCP Server

{
  "mcpServers": {
    "aws-bedrock-data-automation": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "AWS_BUCKET_NAME",
        "-e",
        "AWS_REGION",
        "-e",
        "AWS_PROFILE",
        "mcp/aws-bedrock-data-automation-mcp-server"
      ],
      "env": {
        "AWS_BUCKET_NAME": "your-s3-bucket-name",
        "AWS_REGION": "us-east-1",
        "AWS_PROFILE": "default"
      }
    }
  }
}

Why is it safer to run MCP Servers with Docker?