aws-mcp-setup
npx machina-cli add skill zxkane/aws-skills/aws-mcp-setup --openclawAWS 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 list
If 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:
-
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" ] -
Environment Variables:
"env": { "AWS_ACCESS_KEY_ID": "...", "AWS_SECRET_ACCESS_KEY": "...", "AWS_REGION": "us-west-2" } -
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 |
Source
git clone https://github.com/zxkane/aws-skills/blob/main/plugins/aws-common/skills/aws-mcp-setup/SKILL.mdView on GitHub Overview
Configure AWS MCP tools for AI agents to query up-to-date AWS knowledge, APIs, and best practices. Choose between a Full AWS MCP Server that can execute API calls or an AWS Documentation MCP Server for documentation search only.
How This Skill Works
First, verify existing MCP configuration. Then pick Option A (Full AWS MCP Server) or Option B (AWS Documentation MCP Server). The full server uses uvx with mcp-proxy-for-aws and supports AWS credentials via profile, environment variables, or IAM roles; the docs-only option uses an HTTP MCP server pointed at the knowledge endpoint for search-only capabilities.
When to Use It
- When the agent must execute AWS API calls live (full MCP server).
- When you only need AWS knowledge via documentation search (AWS Documentation MCP).
- When you have no Python/uvx environment but still need docs access (docs MCP).
- When you want to operate with read-only access to AWS tools (use --read-only).
- When you need to verify or adjust existing MCP configuration across local/project/user scopes.
Quick Start
- Step 1: Check existing configuration with claude mcp list and inspect project/user config files.
- Step 2: Choose Option A (full MCP) or Option B (docs MCP) and add the corresponding mcpServers entry.
- Step 3: Apply changes, restart Claude if needed, and verify with sample AWS queries or searches.
Best Practices
- Verify uvx availability and Python 3.10+ before enabling the full MCP.
- Apply least-privilege IAM permissions for AWS MCP actions.
- Prefer the Docs MCP option when API execution is not required.
- Version-control mcpServers configurations and audit changes.
- Test connectivity and responses regularly using claude mcp list and sample queries.
Example Use Cases
- Developer enables a Full AWS MCP Server on a Python 3.10+ host with uvx to allow live AWS API calls.
- Team configures AWS Documentation MCP Server to empower agents with AWS knowledge search only.
- Use AWS_PROFILE to configure credentials for MCP without embedding secrets.
- Project adds mcpServers entries in .mcp.json and validates with claude mcp list.
- Agent runs on EC2 with an IAM Role and uses the Full MCP Server without extra credential config.