SST is a framework for building full-stack serverless applications on AWS with a focus on local development and infrastructure-as-code patterns. It provides TypeScript-first tooling, local debugging, and automated infrastructure deployment.
11 of 33 checks passed. 14 unscored.
Can an agent find and understand this tool without a web search?
Can an agent create an account and get credentials without human intervention?
Can an agent operate autonomously without upfront payment or contracts?
How well does the API work for non-human consumers?
Does the tool fail gracefully when an agent makes a mistake?
SST is primarily a local development framework and CLI tool rather than an API-first service, making it poorly suited for agent discovery and autonomous interaction. The tool lacks MCP server, OpenAPI spec, and llms.txt documentation—agents would need to rely on CLI parsing or programmatic spawning of processes. AWS credential setup is required upfront, and there's no programmatic account creation pathway; agents would need pre-configured AWS access. While the TypeScript SDK and infrastructure code patterns are well-documented, the framework's design assumes human developers running it locally rather than autonomous agents orchestrating deployments remotely.
Install the Agent Native Registry MCP server. Your agents can search, compare, and score tools mid-task.
claude mcp add --transport http agent-native-registry https://agentnativeregistry.com/api/mcp