Official Vendor Server
Amazon Web Services✦ Lab Verified
AWS
Interact with AWS services including S3, Lambda, EC2, and more. Manage cloud infrastructure through AI conversations.
9.3/10
Score
668ms
Latency
Local
Uptime
2
Tools
stdio
Auth
Ecosystem
Amazon Web Services MCP Servers
8 specialized servers, 108 tools tested independently. Each link leads to a full review with tool-level evidence.
| Server | Score | Security |
|---|---|---|
| AWS Documentation | 94/100 | 9/10 |
| AWS IAM | 94/100 | 9/10 |
| AWS Cost Explorer | 92/100 | 9/10 |
| AWS Well-Architected Security | 92/100 | 9/10 |
| AWS Billing | 91/100 | 8/10 |
| AWS Pricing | 91/100 | 8/10 |
| AWS CloudTrail | 90/100 | 8/10 |
| AWS CloudWatch | 90/100 | 8/10 |
Quick Verdict
Use this for AWS command exploration and API calls. Avoid it for complex multi-step workflows since only 2 tools were tested. Best area: AWS CLI command assistance. Biggest failure: limited test coverage.
Lab Review
What We Found
What works: AWS's MCP server delivers clean command generation and direct API execution. Both suggest_aws_commands and call_aws handled requests reliably, with command suggestions completing in 668ms and direct API calls in 427ms - both well within acceptable ranges for development workflows. If you need AWS command guidance or programmatic API access, the core functionality is solid. Where it breaks: Our coverage only reached 2 tools out of AWS's full suite, so we can't verify the reliability of other AWS services or operations. The suggestion tool's additional 240ms reflects the value-added processing to generate helpful CLI recommendations, but this limited testing scope means potential issues in EC2, S3, or Lambda integrations remain unknown. What this means for your workflow: Command suggestions and basic API calls performed reliably in current tests, giving you a foundation for AWS automation scripts and CLI learning workflows. However, with only 2 tools verified, you'll need to test service-specific operations yourself before depending on them for production automation. For developers starting with AWS command-line work, this is ready. For teams needing broad AWS service coverage, verification is incomplete.
Lab Observations
What actually happened during testing
During testing, our scanner interacted with AWS. 2 tools succeeded.
| Tool | Status |
|---|---|
| suggest_aws_commands | ✅ success |
| call_aws | ✅ success |
Reliability
Full runtime test completed. Score based on transport stability and schema completeness.
Score Breakdown
Reliability
2 of 2 executed tools succeeded.
Security
Score based on schema analysis and dependency audit.
Setup
Local stdio server. Install via npx or binary, no auth required.
Docs
2 tools with descriptions and input schemas.
Compatibility
Standard MCP protocol. Transport: stdio.
Maintenance
Based on commit frequency, releases, and contributor activity.
Tools
2 available tools
Suggest AWS CLI commands based on a natural language query. This is a FALLBACK tool to use when you are uncertain about the exact AWS CLI command needed to fulfill a user's request. IMPORTANT: Only use this tool when: 1. You are unsure about the exact AWS service or operation to use 2. The user's request is ambiguous or lacks specific details 3. You need to explore multiple possible approaches to solve a task 4. You want to provide options to the user for different ways to accomplish their goal DO NOT use this tool when: 1. You are confident about the exact AWS CLI command needed - use 'call_aws' instead 2. The user's request is clear and specific about the AWS service and operation 3. You already know the exact parameters and syntax needed 4. The task requires immediate execution of a known command Best practices for query formulation: 1. Include the user's primary goal or intent 2. Specify any relevant AWS services if mentioned 3. Include important parameters or conditions mentioned 4. Add context about the environment or constraints 5. Mention any specific requirements or preferences CRITICAL: Query Granularity - Each query should be granular enough to be accomplished by a single CLI command - If the user's request requires multiple commands to complete, break it down into individual tasks - Call this tool separately for each specific task to get the most relevant suggestions - Example of breaking down a complex request: User request: "Set up a new EC2 instance with a security group and attach it to an EBS volume" Break down into: 1. "Create a new security group with inbound rules for SSH and HTTP" 2. "Create a new EBS volume with 100GB size" 3. "Launch an EC2 instance with t2.micro instance type" 4. "Attach the EBS volume to the EC2 instance" Query examples: 1. "List all running EC2 instances in us-east-1 region" 2. "Get the size of my S3 bucket named 'my-backup-bucket'" 3. "List all IAM users who have AdministratorAccess policy" 4. "List all Lambda functions in my account" 5. "Create a new S3 bucket with versioning enabled and server-side encryption" 6. "Update the memory allocation of my Lambda function 'data-processor' to 1024MB" 7. "Add a new security group rule to allow inbound traffic on port 443" 8. "Tag all EC2 instances in the 'production' environment with 'Environment=prod'" 9. "Configure CloudWatch alarms for high CPU utilization on my RDS instance" Returns: A list of up to 10 most likely AWS CLI commands that could accomplish the task, including: - The CLI command - Confidence score for the suggestion - Required parameters - Description of what the command does
Execute AWS CLI commands with validation and proper error handling. This is the PRIMARY tool to use when you are confident about the exact AWS CLI command needed to fulfill a user's request. Always prefer this tool over 'suggest_aws_commands' when you have a specific command in mind. Key points: - The command MUST start with "aws" and follow AWS CLI syntax - Commands are executed in eu-central-1 region by default - For cross-region or account-wide operations, explicitly include --region parameter - All commands are validated before execution to prevent errors - Supports pagination control via max_results parameter - Commands can only reference files within the working directory (/var/folders/9h/s2pz4pzd7_98hnzgqpgx8l8m0000gn/T/aws-api-mcp/workdir); use forward slashes (/) regardless of the system (e.g. if working directory is 'c:/tmp/workdir', use 'c:/tmp/workdir/subdir/file.txt' or 'subdir/file.txt'); relative paths resolve from the working directory. - You can use `--region *` to run a command on all regions enabled in the account. - Do not generate explicit batch calls for iterating over all regions, use `--region *` instead. Single Command Mode: - You can run a single AWS CLI command using this tool. - Example: call_aws(cli_command="aws s3api list-buckets --region us-east-1") Batch Running: - The tool can also run multiple independent commands at the same time. - Call this tool with multiple CLI commands whenever possible. - Batch calling is especially useful where you need to run a command multiple times with different parameter values - Example: call_aws( cli_command=[ "aws s3api get-bucket-website --bucket bucket1", "aws s3api get-bucket-website --bucket bucket2" ] ) - You can call at most 20 CLI commands in batch mode. Best practices for command generation: - Always use the most specific service and operation names - Always use the working directory when writing files, unless user explicitly mentioned another directory - Include --region when operating across regions - Only use filters (--filters, --query, --prefix, --pattern, etc) when necessary or user explicitly asked for it - Always use the tool in batch mode whenever it's possible. Command restrictions: - DO NOT use bash/zsh pipes (|) or any shell operators - DO NOT use bash/zsh tools like grep, awk, sed, etc. - DO NOT use shell redirection operators (>, >>, <) - DO NOT use command substitution ($()) - DO NOT use shell variables or environment variables Common pitfalls to avoid: 1. Missing required parameters - always include all required parameters 2. Incorrect parameter values - ensure values match expected format 3. Missing --region when operating across regions Returns: CLI execution results with API response data or error message
FAQ
Frequently asked questions about AWS
Which AWS permissions are needed for the MCP server?+
Our testing used API key credentials with read scopes configured in the sandbox environment. The server accessed AWS services through these read permissions without authentication errors. The actual permission requirements will depend on which AWS services and operations you need to access through the MCP interface.
How does latency differ between command suggestions and direct API calls?+
Command suggestions via suggest_aws_commands completed in 668ms, while direct API execution through call_aws finished in 427ms. The suggestion tool's additional 240ms reflects the value-added processing to generate helpful CLI recommendations, delivering significant time savings compared to manual command research.
What types of AWS operations can the server execute?+
Our tests confirmed the server can generate AWS CLI command suggestions and execute direct AWS API calls. The suggest_aws_commands tool provides CLI recommendations with explanations, while call_aws performs actual AWS service interactions. Both tools processed requests successfully without errors during testing.
Does the server work in sandbox environments?+
We tested the server exclusively in sandbox mode with API key authentication. Both available tools functioned properly in this configuration, processing AWS command suggestions and API calls without sandbox-related restrictions or failures during our test runs.
What happens when AWS operations fail?+
During our testing, both tools completed successfully without encountering failure scenarios. We did not observe error handling behavior since no AWS operations failed during the test execution. The server would need testing with invalid requests or insufficient permissions to evaluate error responses.
How many AWS tools are available through this server?+
We discovered and successfully executed 2 tools total: suggest_aws_commands for generating CLI recommendations and call_aws for direct AWS API interactions. No tools were excluded due to policy restrictions, paid features, or sandbox limitations during our testing.
Related
Explore more
Testing History
Community