
Aws Mcp Setup
- 534 installs
- 342 repo stars
- Updated June 15, 2026
- zxkane/aws-skills
aws-mcp-setup is an agent skill that configures AWS MCP servers for documentation search and optional authenticated AWS API access in Claude-compatible agents.
About
aws-mcp-setup is an agent skill that walks solo builders through wiring AWS MCP servers into Claude-style clients. It compares a full server that needs uvx and AWS credentials against a lightweight documentation MCP that needs no login, so you can choose speed-to-try versus operational depth. The guide starts with detecting what is already active—tool name patterns from /mcp and on-disk MCP JSON—before rewriting configuration, which reduces duplicate servers and broken precedence. It is aimed at indie developers shipping on AWS who want agents to search official docs and, when appropriate, call APIs safely. Use it when you mention aws-mcp, awsdocs, MCP connectivity problems, or first-time Claude MCP configuration for AWS.
- Two-path setup: Full AWS MCP (Python 3.10+, uvx, credentials) vs Documentation MCP (no auth)
- Preflight checks via /mcp tool patterns and hierarchical mcp.json / claude.json config
- Troubleshooting connectivity and aws-mcp / awsdocs / uvx installation issues
- Allowed agent bash flows: which, aws sts get-caller-identity, claude mcp, config cat
- Documents execute AWS API calls plus doc search vs documentation search only
Aws Mcp Setup by the numbers
- 534 all-time installs (skills.sh)
- Ranked #1,697 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Security screen: MEDIUM risk (skills.sh audit)
- Data as of Aug 3, 2026 (Skillselion catalog sync)
npx skills add https://github.com/zxkane/aws-skills --skill aws-mcp-setupAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 534 |
|---|---|
| repo stars | ★ 342 |
| Security audit | 1 / 3 scanners passed |
| Last updated | June 15, 2026 |
| Repository | zxkane/aws-skills ↗ |
What it does
Connect Claude Code or similar agents to AWS documentation search and optional live AWS API calls through MCP.
Who is it for?
Best when you're standardizing AWS MCP on one machine or repo before building cloud-backed agent workflows.
Skip if: Skip if you only need occasional AWS doc lookups in a browser without any agent or MCP integration.
When should I use this skill?
Setting up AWS MCP, configuring AWS documentation tools, troubleshooting MCP connectivity, or when the user mentions aws-mcp, awsdocs, uvx setup, or MCP server configuration.
What you get
You get a verified MCP layout—full AWS server or docs-only—with working connectivity checks and clear credential requirements for API execution.
- Working AWS or awsdocs MCP entry in agent configuration
- Confirmed tool visibility via /mcp or config inspection
By the numbers
- Two MCP options documented: Full AWS MCP Server vs AWS Documentation MCP
- Full server requires Python 3.10+, uvx, and AWS credentials
Files
AWS MCP Server Configuration Guide
Overview
This guide helps you configure AWS MCP tools for AI agents. Two options are available:
| Option | Requirements | Capabilities |
|---|---|---|
| Full AWS MCP Server | Python 3.10+, uvx, AWS credentials | Execute AWS API calls + documentation search |
| AWS Documentation MCP | None | Documentation search only |
Step 1: Check Existing Configuration
Before configuring, check if AWS MCP tools are already available using either method:
Method A: Check Available Tools (Recommended)
Look for these tool name patterns in your agent's available tools:
mcp__aws-mcp__*ormcp__aws__*→ Full AWS MCP Server configuredmcp__*awsdocs*__aws___*→ AWS Documentation MCP configured
How to check: Run /mcp command to list all active MCP servers.
Method B: Check Configuration Files
Agent tools use hierarchical configuration (precedence: local → project → user → enterprise):
| Scope | File Location | Use Case |
|---|---|---|
| Local | .claude.json (in project) | Personal/experimental |
| Project | .mcp.json (project root) | Team-shared |
| User | ~/.claude.json | Cross-project personal |
| Enterprise | System managed directories | Organization-wide |
Check these files for mcpServers containing aws-mcp, aws, or awsdocs keys:
# Check project config
cat .mcp.json 2>/dev/null | grep -E '"(aws-mcp|aws|awsdocs)"'
# Check user config
cat ~/.claude.json 2>/dev/null | grep -E '"(aws-mcp|aws|awsdocs)"'
# Or use Claude CLI
claude mcp listIf AWS MCP is already configured, no further setup needed.
Step 2: Choose Configuration Method
Automatic Detection
Run these commands to determine which option to use:
# Check for uvx (requires Python 3.10+)
which uvx || echo "uvx not available"
# Check for valid AWS credentials
aws sts get-caller-identity || echo "AWS credentials not configured"Option A: Full AWS MCP Server (Recommended)
Use when: uvx available AND AWS credentials valid
Prerequisites:
- Python 3.10+ with
uvpackage manager - AWS credentials configured (via profile, environment variables, or IAM role)
Required IAM Permissions:
{
"Version": "2012-10-17",
"Statement": [{
"Effect": "Allow",
"Action": [
"aws-mcp:InvokeMCP",
"aws-mcp:CallReadOnlyTool",
"aws-mcp:CallReadWriteTool"
],
"Resource": "*"
}]
}Configuration (add to your MCP settings):
{
"mcpServers": {
"aws-mcp": {
"command": "uvx",
"args": [
"mcp-proxy-for-aws@latest",
"https://aws-mcp.us-east-1.api.aws/mcp",
"--metadata", "AWS_REGION=us-west-2"
]
}
}
}Credential Configuration Options:
1. AWS Profile (recommended for development):
"args": [
"mcp-proxy-for-aws@latest",
"https://aws-mcp.us-east-1.api.aws/mcp",
"--profile", "my-profile",
"--metadata", "AWS_REGION=us-west-2"
]2. Environment Variables:
"env": {
"AWS_ACCESS_KEY_ID": "...",
"AWS_SECRET_ACCESS_KEY": "...",
"AWS_REGION": "us-west-2"
}3. IAM Role (for EC2/ECS/Lambda): No additional config needed - uses instance credentials
Additional Options:
--region <region>: Override AWS region--read-only: Restrict to read-only tools--log-level <level>: Set logging level (debug, info, warning, error)
Reference: https://github.com/aws/mcp-proxy-for-aws
Option B: AWS Documentation MCP Server (No Auth)
Use when:
- No Python/uvx environment
- No AWS credentials
- Only need documentation search (no API execution)
Configuration:
{
"mcpServers": {
"awsdocs": {
"type": "http",
"url": "https://knowledge-mcp.global.api.aws"
}
}
}Step 3: Verification
After configuration, verify tools are available:
For Full AWS MCP:
- Look for tools:
mcp__aws-mcp__aws___search_documentation,mcp__aws-mcp__aws___call_aws
For Documentation MCP:
- Look for tools:
mcp__awsdocs__aws___search_documentation,mcp__awsdocs__aws___read_documentation
Troubleshooting
| Issue | Cause | Solution |
|---|---|---|
uvx: command not found | uv not installed | Install with pip install uv or use Option B |
AccessDenied error | Missing IAM permissions | Add aws-mcp:* permissions to IAM policy |
InvalidSignatureException | Credential issue | Check aws sts get-caller-identity |
| Tools not appearing | MCP not started | Restart your agent after config change |
Related skills
How it compares
Use for MCP server wiring and troubleshooting, not as a substitute for IAM policy design or application deployment runbooks.
FAQ
Who is aws-mcp-setup for?
Developers using Claude Code, Cursor, or similar agents who deploy or integrate with AWS and want MCP documented and working.
When should I use aws-mcp-setup?
During Build when standing up agent-tooling: first AWS MCP install, fixing uvx or credential errors, or choosing docs-only MCP versus full API access before feature work.
Is aws-mcp-setup safe to install?
The skill guides identity checks and config reads; review the Security Audits panel on this Prism page and treat full-server mode as requiring scoped AWS credentials you control.