Skip to main content
Glama

aws_execute

Execute AWS API calls for services and operations not covered by other tools, with safety controls for read-only mode and sensitive data access.

Instructions

Execute any AWS API call by specifying service, method, and parameters. Use this for AWS operations not covered by other tools. In --readonly mode: read-only operations pass through, mutating operations with DryRun support run as dry-run, and all other mutations are blocked.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
profileNoAWS profile name from ~/.aws/config (e.g., 'default', 'production')
regionNoAWS region override (e.g., 'us-east-1', 'sa-east-1')
sensitive_access_tokenNoOut-of-band approval token configured in AWS_MCP_SENSITIVE_ACCESS_TOKEN. Required for operations that can return decrypted or secret values.
sensitive_access_reasonNoShort human reason for retrieving sensitive data. Required for auditability.
sensitive_access_acknowledgedNoMust be true to confirm that the response may contain secret or decrypted data.
serviceYesAWS service name as used by boto3 (e.g., 'ec2', 's3', 'lambda', 'ecs', 'rds', 'dynamodb', 'sqs', 'sns')
methodYesAPI method name in snake_case (e.g., 'describe_instances', 'list_buckets', 'get_function')
parametersNoMethod parameters as key-value pairs matching the boto3 API (e.g., {"InstanceIds": ["i-1234"], "DryRun": false})
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden and successfully discloses the readonly mode security policy (mutation handling) and implicitly signals sensitive data handling via references to decrypted values. Minor gap: doesn't describe output format or pagination behavior typical of AWS API responses.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences with zero waste: purpose first, sibling differentiation second, behavioral guardrails third. Every sentence earns its place with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of a generic AWS API executor and lack of output schema, the description appropriately covers critical safety aspects (readonly mode, sensitive data acknowledgment). Minor gap: could note that return values vary by underlying AWS service/method.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 100% description coverage (all 8 parameters documented), establishing baseline 3. Description mentions 'service, method, and parameters' generally but doesn't add semantic depth beyond the schema's 'boto3 API' references.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description provides a specific verb ('Execute') and resource ('any AWS API call') and explicitly distinguishes from 200+ sibling tools with 'Use this for AWS operations not covered by other tools,' making the fallback/escape-hatch positioning crystal clear.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use ('Use this for AWS operations not covered by other tools') and details the readonly mode behavior with three specific cases (pass-through, dry-run, blocked), providing clear operational guardrails.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/marcelobrake/aws-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server