skills.rest
farslab
farslabCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

aws-mcp-setup

Configure AWS MCP servers for documentation search and API access.

Updated Aug 22, 2026
Search Tags:#aws#configuration#mcp#iam#documentation search#uvx#api access
One-click install
npx skills add https://github.com/farslab/claude-skills --skill aws-mcp-setup-farslab
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: aws-mcp-setup
Source: https://github.com/farslab/claude-skills/tree/main/aws-mcp-setup
Command: npx skills add https://github.com/farslab/claude-skills --skill aws-mcp-setup-farslab

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Setting up AWS MCP servers involves choosing between multiple configuration options, verifying prerequisites like uvx and AWS credentials, and debugging connectivity issues. This Skill guides you through detecting existing configurations, selecting the right setup path, and verifying that AWS tools are available to your AI agent. ## Core Features & Use Cases - Automatic Environment Detection: Checks for uvx availability and valid AWS credentials to recommend the correct configuration path. - Two Configuration Options: Supports the Full AWS MCP Server (uvx + credentials for API execution and docs search) and the lightweight AWS Documentation MCP (no auth, docs search only). - Troubleshooting Guidance: Resolves common issues like missing uvx, IAM permission errors, invalid signatures, and tools not appearing after setup. - Use Case: You want your AI agent to search AWS documentation and execute read-only AWS API calls. Run the detection commands, add the provided mcpServers JSON block to your .mcp.json, and verify the mcp__aws-mcp__ tools appear. ## Quick Start Ask the agent to check whether AWS MCP is already configured and set up the appropriate AWS MCP server for my environment.

Frequently Asked Questions about aws-mcp-setup

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I configure an AWS MCP server for my AI agent?▼

Add an mcpServers entry to your .mcp.json or ~/.claude.json file. For full API access, use uvx with mcp-proxy-for-aws pointing to https://aws-mcp.us-east-1.api.aws/mcp; for documentation only, use the HTTP endpoint https://knowledge-mcp.global.api.aws.

What is the difference between Full AWS MCP and AWS Documentation MCP?▼

The Full AWS MCP Server requires Python 3.10+, uvx, and AWS credentials, and supports both API execution and documentation search. The Documentation MCP needs no authentication and only provides documentation search and reading.

Can I use AWS MCP without AWS credentials?▼

Yes, the AWS Documentation MCP server works without any credentials or local Python environment. It connects via HTTP to knowledge-mcp.global.api.aws and provides documentation search only, with no API execution capability.

What IAM permissions does the AWS MCP server need?▼

The Full AWS MCP Server requires the aws-mcp:InvokeMCP, aws-mcp:CallReadOnlyTool, and aws-mcp:CallReadWriteTool actions in your IAM policy. Credentials can come from an AWS profile, environment variables, or an IAM instance role.

Why are AWS MCP tools not appearing after configuration?▼

Tools usually fail to appear because the agent was not restarted after the config change, uvx is not installed, or credentials are invalid. Verify with aws sts get-caller-identity and check the server list with claude mcp list.

Related Skills

Explore More Software Engineering Skills→
awsaws
2.3k

setting-up-ec2-instance-profiles

Configure EC2 instances with IAM roles and instance profiles for AWS service access.

Official
Advanced
hongmaple0820hongmaple0820
9

aws-mcp-setup

Configure AWS MCP servers for API calls and documentation lookups.

Community
Intermediate
dengineproblemdengineproblem

s3-bucket-policy

Create and analyze AWS S3 bucket policies for access control.

Community
Advanced
huggingfacehuggingface
10.9k

hf-cloud-python-env-setup

Create an isolated Python environment with boto3 for SageMaker and AWS deployments.

Official
Advanced