# awslabs/mcp

Open source MCP Servers for AWS

Repository: https://github.com/awslabs/mcp
Canonical: https://ross.abutalabs.com/products/mcp
Homepage: https://awslabs.github.io/mcp/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: aws, mcp, mcp-client, mcp-clients, mcp-host, mcp-server, mcp-servers, mcp-tools, modelcontextprotocol
Last push: 2026-08-26T18:24:36+00:00

## Health v2 (maintenance only)
Score: 82/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 37
- inputs: {"age_days": 531, "days_push": 7, "days_rel": 7, "gap_med": 1, "n_releases_24m": 224}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 9641, forks 1733 (observed 2026-08-28T04:10:36.489722+00:00)

## What it is
A suite of open-source Model Context Protocol (MCP) servers from AWS Labs that expose AWS services, documentation, and best practices to LLM applications and AI coding assistants. It lets MCP clients like Cursor, Claude Desktop, and Cline interact with AWS resources and guidance through a standardized protocol.

## Use cases
- connect AI coding assistants to AWS services via MCP
- give LLMs real-time access to official AWS documentation
- manage AWS infrastructure and deployments from an AI agent
- query AWS databases and analytics services through an MCP client
- build AI workflows that automate AWS cost and operations tasks
- integrate AWS capabilities into chatbots and IDEs

## When to choose
- you use MCP-compatible clients like Cursor, Claude Desktop, or Cline and work heavily with AWS
- you want AI-assisted AWS infrastructure, deployment, or documentation workflows
- you need standardized, open-source MCP servers for many AWS services in one repo

## When to avoid
- you are building production agent software and prefer the newer AWS Agent Toolkit
- you use a cloud provider other than AWS
- your AI tooling does not support the Model Context Protocol

## Facets
- artifact type: service
- maturity: active
- function: mcp, agent-framework, developer-tools, documentation, infrastructure-as-code, cloud
- domain: artificial-intelligence, cloud-computing, developer-tools, large-language-models
- platform: python, cross-platform, cli
- tags: aws, model-context-protocol, mcp-servers, llm-tools, ai-coding-assistants, cloud-automation, ai-agents

## Member repositories
- awslabs/mcp (main) score 82

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:36.489722+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:21:20.347234+00:00, confidence not recorded.
  - readme: https://github.com/awslabs/mcp (fetched 2026-08-28T04:10:36.489722+00:00, sha 9cc2fed3f9ff)
  - homepage: https://awslabs.github.io/mcp/ (fetched 2026-08-29T08:21:07.161980+00:00, sha ab6b841c3773)
- Data as of 2026-08-30T08:39:29.467469+00:00.