ModelsAtlas
Explore
Atlas / MCP servers / zxkane / Amazon Bedrock

Amazon BedrockSAFE

mcp/zxkane/amazon-bedrock
MCP server by zxkane · amazon bedrock · amazon nova · claude · Audited 2026-10-09
⚑ Report / re-scanSource ↗

Model Context Procotol(MCP) server for using Amazon Bedrock Nova Canvas to generate images

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
1 1r · 0w · 0d
Transport
stdio
License
MIT
Stars
25
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://mseep.ai/app/zxkane-mcp-server-amazon-bedrock)

A Model Control Protocol (MCP) server that integrates with Amazon Bedrock's Nova Canvas model for AI image generation.

Features

  • High-quality image generation from text descriptions using Amazon's Nova Canvas model
  • Advanced control through negative prompts to refine image composition
  • Flexible configuration options for image dimensions and quality
  • Deterministic image generation with seed control
  • Robust input validation and error handling

Prerequisites

  1. Active AWS account with Amazon Bedrock and Nova Canvas model access
  2. Properly configured AWS credentials with required permissions
  3. Node.js version 18 or later

Installation

AWS Credentials Configuration

The server requires AWS credentials with appropriate Amazon Bedrock permissions. Configure these using one of the following methods:

  1. Environment variables:
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
  1. AWS credentials file (~/.aws/credentials):
[the_profile_name]
aws_access_key_id = your_access_key
aws_secret_access_key = your_secret_key

Environment variable for active profile:

export AWS_PROFILE=the_profile_name
  1. IAM role (when deployed on AWS infrastructure)

Claude Desktop Integration

To integrate with Claude Desktop, add the following configuration to your settings file:

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

{
"mcpServers": {
"a
Read from source at commit e28bd7b3b66dOBSERVED · 2026-10-09
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code
claude mcp add mcp-server-amazon-bedrock --env AWS_ACCESS_KEY_ID=${AWS_ACCESS_KEY_ID} --env AWS_SECRET_ACCESS_KEY=${AWS_SECRET_ACCESS_KEY} --env AWS_SESSION_TOKEN=${AWS_SESSION_TOKEN} -- npx -y @zxkane/[email protected]
claude-desktop
{
  "mcpServers": {
    "mcp-server-amazon-bedrock": {
      "command": "npx",
      "args": [
        "-y",
        "@zxkane/[email protected]"
      ],
      "env": {
        "AWS_ACCESS_KEY_ID": "${AWS_ACCESS_KEY_ID}",
        "AWS_SECRET_ACCESS_KEY": "${AWS_SECRET_ACCESS_KEY}",
        "AWS_SESSION_TOKEN": "${AWS_SESSION_TOKEN}"
      }
    }
  }
}
03

Exposed tools (1)

1 read · 0 write · 0 destructive.

ToolRiskDescription
generate_imagereadGenerate image(s) using Amazon Nova Canvas model. The returned data is Base64-encoded string that represent each image that was generated.
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (1 observation(s))
Network
none-observed
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (3)

LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
example-client/src/index.ts:30
command: path.resolve(__dirname, "../../build/index.js"),
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
example-client/package.json
@modelcontextprotocol/sdk, terminal-image, typescript
Why it matters. 3 dependency range(s) float
Fix. pin exact versions or ship a lockfile
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@aws-sdk/client-bedrock-runtime, @aws-sdk/credential-providers, zod, @types/node, typescript
Why it matters. 5 dependency range(s) float
Fix. pin exact versions or ship a lockfile

Gates applied: no_behavioural_pass.

Audited 2026-10-09 · audit v0.4.1 · source sha e28bd7b3b66dfull audit observations/trust-audit/mcp-server/zxkane__amazon-bedrock.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-09e28bd7b3b66dSAFEB89first audit
06

Questions

What is the Amazon Bedrock MCP server?

Model Context Procotol(MCP) server for using Amazon Bedrock Nova Canvas to generate images

What tools does Amazon Bedrock expose?

1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Amazon Bedrock safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does Amazon Bedrock need?

It reads AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY and AWS_SESSION_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does Amazon Bedrock run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as @zxkane/mcp-server-amazon-bedrock at 0.1.1.

How current is this page?

The grade is for one exact copy of the source (e28bd7b3b66d), read on 2026-10-09. The repository is watched and re-audited when it changes.

Advertisement