Skip to main content
Glama
@yawlabs/aws-mcp

@yawlabs/aws-mcp

Official
by YawLabs

aws_login_start

Starts an AWS SSO device-code login without opening a browser and returns a verification URL and code for the user to authenticate; call aws_login_complete afterward to confirm.

Instructions

Start an AWS SSO login via the device-code flow (no browser spawned from this process). Returns a verification URL and short code -- surface these to the user so they can open the URL in their own browser and paste the code. After they auth, call aws_login_complete with the returned sessionId to confirm completion. For a user with NO profile yet, pass ssoSession plus startUrl and ssoRegion instead of profile: this writes a managed [sso-session] block to the AWS config file (never touching one the user wrote) and logs in to IAM Identity Center directly; then use aws_sso_list_assignments and aws_sso_generate_profiles.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "aws_login_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
profileNoAWS profile configured for SSO. Defaults to $AWS_PROFILE or 'default'. Mutually exclusive with ssoSession.
startUrlNoIdentity Center start URL (https://...). Only with ssoSession.
ssoRegionNoRegion of the Identity Center instance, e.g. us-east-1. Only with ssoSession.
ssoSessionNoLog in to an IAM Identity Center sso-session directly, without any profile. Use with startUrl + ssoRegion to create the [sso-session] block on first use; omit them to log in to an existing block.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv2.7.1
    • changedInput schema / properties / profile / description
      Previous value: -"AWS profile configured for SSO. Defaults to $AWS_PROFILE or 'default'."New value: +"AWS profile configured for SSO. Defaults to $AWS_PROFILE or 'default'. Mutually exclusive with ssoSession."
    • addedInput schema / properties / ssoRegion
      Added value: +{
      +  "description": "Region of the Identity Center instance, e.g. us-east-1. Only with ssoSession.",
      +  "type": "string"
      +}
    • addedInput schema / properties / ssoSession
      Added value: +{
      +  "description": "Log in to an IAM Identity Center sso-session directly, without any profile. Use with startUrl + ssoRegion to create the [sso-session] block on first use; omit them to log in to an existing block.",
      +  "type": "string"
      +}
    • addedInput schema / properties / startUrl
      Added value: +{
      +  "description": "Identity Center start URL (https://...). Only with ssoSession.",
      +  "type": "string"
      +}
  2. First observedv1.3.2

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only say not-read-only, open-world, non-idempotent, non-destructive; the description adds real behavior: no browser is launched, a verification URL and short code are returned and must be surfaced to the user, and the no-profile path writes a managed [sso-session] block to the AWS config file while never touching a user-written block. That last point is a material side effect the annotations do not convey.

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

Conciseness4/5

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

The description is front-loaded with the core action and return values before branching into the no-profile case, and every sentence carries actionable content. It is dense and the third sentence runs long, but nothing is redundant padding.

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

Completeness5/5

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

With no output schema, the description compensates by naming the return values (verification URL and short code) and the sessionId consumed by the next call. It also covers the config-file side effect and the follow-up tool chain, so an agent can complete the whole login flow from this text alone.

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

Parameters4/5

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

Schema coverage is 100%, so the parameter descriptions already carry the basics; the description adds scenario-level meaning by explaining when to prefer ssoSession over profile and that omitting startUrl/ssoRegion targets an existing sso-session block. It stops short of restating parameter formats, which is appropriate given the schema.

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 gives a specific verb and resource ("Start an AWS SSO login") and immediately qualifies the mechanism (device-code flow, no browser spawned). It is clearly distinguishable from aws_login_complete, which it names as the follow-up step, and from profile-listing/session siblings.

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?

It states explicit when-to-use branches: use profile by default, use ssoSession + startUrl + ssoRegion only for a user with NO profile yet, and call aws_login_complete with the returned sessionId afterward. It even names the downstream tools (aws_sso_list_assignments, aws_sso_generate_profiles) for the no-profile path.

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