Skip to main content
MCP server CX Codex

AWS Labs Nova Canvas — Claude Code MCP server: what it does

AWS Labs Nova Canvas generates AI images with Amazon Nova Canvas directly in your coding assistant via the Model Context Protocol.

Apache-2.0 ★ 9,939 updated 2026-10-23

Open on GitHub

What AWS Labs Nova Canvas does

This MCP server integrates the Amazon Nova Canvas model into coding assistants like Claude Code. It allows agents to generate image assets on demand without leaving the active editor session.

The tool is distributed under the Apache-2.0 license as part of the awslabs/mcp collection. Running it requires active AWS infrastructure access with permission to call Amazon Nova Canvas.

AWS Labs is moving core components from this repository toward the Agent Toolkit for AWS, while keeping this codebase open for community updates.

What it helps with

  • generate visual assets using Amazon Nova Canvas inside an editor chat
  • connect the Nova Canvas model to IDE agents via the Model Context Protocol
  • automate image creation for projects without opening the AWS management console

Example prompts for the agent

  • Generate a hero banner for our homepage using Nova Canvas
  • Create an illustration of a cloud architecture setup with Amazon Nova Canvas

How to install AWS Labs Nova Canvas

Install

The MCP registry has no launch command for it: see the repository README

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about AWS Labs Nova Canvas

How to install AWS Labs Nova Canvas in Claude Code?

You set up MCP servers from the awslabs/mcp repository in Claude Code by defining their entry in the project's .mcp.json file.

What does AWS Labs Nova Canvas do?

It gives your coding assistant tools to create images through Amazon Nova Canvas based on text prompts.

What are the prerequisites for this server?

You need valid AWS credentials and configured access to Amazon Nova Canvas services.

Similar MCP servers

All MCP servers for AI and ML →

From the same set36

The whole set →
Amazon ElastiCache/MemoryDB for Valkey Amazon ElastiCache/MemoryDB for Valkey is an MCP server for Claude Code with 12 Valkey tools for search indices, JSON paths and tiered command execution. CX Codex +1 ★ 9,939repo stars Amazon Timestream for InfluxDB Handles Amazon Timestream for InfluxDB clusters and instances, letting your assistant query time-series data and inspect AWS resources. CX Codex +1 ★ 9,939repo stars AWS S3 Tables The AWS S3 Tables MCP server lets AI agents work with S3 Tables, run read-only SQL, inspect metadata, and turn CSV files in S3 into tables. CX Codex +1 ★ 9,939repo stars Amazon Redshift Amazon Redshift — an MCP server for Redshift that discovers clusters and serverless workgroups, browses schemas and tables, and runs SQL. Read-only unless you opt out. CX Codex +1 ★ 9,939repo stars Amazon ElastiCache for Memcached The Amazon ElastiCache for Memcached MCP server lets an AI agent work with Memcached through standard cache operations. Use it for inspection, debugging, or controlled data access. CX Codex +1 ★ 9,939repo stars AWS IAM Lets your agent create and edit AWS IAM users, roles, groups and policies, with a simulator to test permissions before anything changes. CX Codex +1 ★ 9,939repo stars Amazon ElastiCache Manages Amazon ElastiCache resources via AWS control plane APIs directly from your assistant. It handles serverless caches, replication groups, and CloudWatch metrics. CX Codex +1 ★ 9,939repo stars Amazon DynamoDB Amazon DynamoDB is an MCP server for designing and validating DynamoDB models, generating resources, analyzing source databases, and estimating operation costs. CX Codex +1 ★ 9,939repo stars

Project sponsors

Companies that keep this analytics open