@yawlabs/aws-mcp
OfficialRelated Servers
Alternatives to @yawlabs/aws-mcp
No user-submitted related servers found.
Related Servers
- AlicenseAqualityBmaintenanceMCP server for AWS SSO authentication and profile management, enabling AI assistants to check identity, switch profiles, and manage EC2/EKS resources.8MIT
- AlicenseNot gradedqualityDmaintenanceA minimal, security-focused MCP gateway for connecting ChatGPT to AWS account data through explicit, read-only tools.MIT
- AlicenseAqualityDmaintenanceOne MCP server for the SaaS back office. Stripe, HubSpot, and Google Sheets exposed as typed, read-only-by-default tools for Claude and any MCP client.11MIT
- FlicenseNot gradedqualityDmaintenanceAn MCP server on AWS Lambda that gives AI assistants read-only access to SQS dead-letter queues and CloudWatch logs for fast incident triage.-
- AlicenseCqualityDmaintenanceA Model Context Protocol (MCP) server that enables AI assistants like Claude to interact with your AWS environment. This allows for natural language querying and management of your AWS resources during conversations. Think of better Amazon Q alternative.3296ISC
- FlicenseNot gradedqualityDmaintenanceA single MCP server that exposes safe, permission-checked tools for AI assistants to reach file systems, databases, APIs, Git, cloud services, and business applications.-
TDQS
Scored across 30 tools
Most tools have clearly distinct targets: session get/set/clear, login start/complete, resource CRUD, logs query vs logs tail vs metrics query. The fuzzy area is the generic-execution cluster — aws_call, aws_paginate, aws_multi_region, aws_multi_account and aws_script all 'run an API operation' — but each description explicitly states when to prefer it over aws_call, which resolves the overlap for an attentive agent. A few boundaries (aws_resource_get/list vs aws_call) require reading the description rather than the name alone.
Uniform `aws_` prefix and snake_case throughout, with a small set of clear domain prefixes (logs_, session_, resource_, sso_, docs_, multi_). The only wobble is word-order convention: some names are verb-first (assume_role, list_profiles, create/update/delete via resource_, generate_profiles) and others noun-first (logs_query, session_set, resource_get, iam_simulate). Both patterns are readable and consistent within their sub-families, so it is a minor deviation rather than a mixed-convention mess.
30 tools is on the heavy side for one server, sitting at the top of the '16-25 feels heavy' band and into 25+. The count is defensible because they span genuinely different domains (auth/SSO, session, generic execution, Cloud Control CRUD, logs, metrics, Lambda, docs, IAM simulation, multi-region/account fan-out), but a few could be folded — e.g. aws_paginate is aws_call plus two params, and aws_session_clear/get/set are three thin tools that could be one.
Coverage is broad and lifecycle-complete where it counts: full Cloud Control CRUD plus async status and a dry-run diff, SSO login start/complete, profile listing, role assumption, refresh, and session state control. Multi-region/multi-account fan-out, Lambda invoke with log tail, and a docs search/read pair round it out. Gaps are minor and mostly covered by the aws_call/aws_script escape hatches — no SSO logout, no removal of generated profiles, no query-cancel for aws_logs_query, and no first-class S3 data-plane operations.