# AWS Service Reference Information MCP Server A Model Context Protocol server providing access to AWS Service Reference Information. This server
Aws Service Authorization Reference MCP server exists for a simple reason — assistants are far more useful when they can act on Aws Service Authorization Reference directly instead of describing what you should do. # AWS Service Reference Information MCP Server A Model Context Protocol server providing access to AWS Service Reference Information. This server enables LLMs to retrieve IAM actions, resources and conditions keys. # Blog posts! Here is a.
AWS Service Authorization Reference is a piece of documentation available here where AWS gives exhaustive reference data on all IAM Actions, Resources and Condition Keys, grouping information that was otherwise scattered across multiple service documentations.
@modelcontextprotocol/inspector on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.
Once Aws Service Authorization Reference is connected, these are the calls the assistant has available:
service_codes — Lists all service codes for which we have documentation availableservice_stats — Tells how many Actions, Resources and Condition Keys are documentedservice_actions — A comma-separeted list of all actions for a serviceservice_resources — A comma-separeted list of all resources for a serviceservice_condition_keys — A comma-separeted list of all conditions keys for a serviceservice_action_information — Retrieve the authorization reference data (resources and condition keys) for a single AWS service actionservice_resource_information — Retrieve the authorization reference data (resources and condition keys) for a single AWS service actionservice_condition_key_information — Retrieve the authorization reference data (resources and condition keys) for a single AWS service actionPlenty of cloud and infrastructure servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Aws Service Authorization Reference's toolset — service_codes, service_stats, service_actions and 5 more — is a fair guide to whether it matches your workflow. It is maintained by psantus; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| service_codes | Lists all service codes for which we have documentation available |
| service_stats | Tells how many Actions, Resources and Condition Keys are documented. |
| service_actions | A comma-separeted list of all actions for a service |
| service_resources | A comma-separeted list of all resources for a service |
| service_condition_keys | A comma-separeted list of all conditions keys for a service |
| service_action_information | Retrieve the authorization reference data (resources and condition keys) for a single AWS service action |
| service_resource_information | Retrieve the authorization reference data (resources and condition keys) for a single AWS service action |
| service_condition_key_information | Retrieve the authorization reference data (resources and condition keys) for a single AWS service action |
"mcpServers": {
"aws-service-authorization-reference": {
"command": "uv",
"args": [
"--directory",
"/root/to/folder/aws-service-authorization-reference",
"run",
"main.py"
]
}
}Configuration as documented by the project. Restart the client after saving.
Manage your whole Supabase project in conversation — database, auth, storage, Edge Functions and branches.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.
AWS Labs' official server suite — current AWS docs, CDK guidance, cost analysis and service tools.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.
Workers, KV, R2 and D1 by conversation — Cloudflare's official remote servers for building and observability.
Dashboards, Prometheus and Loki queries, incidents and alerts — observability by conversation.