MCP server · Amazon S3

amazon-s3-mcp.yml

AWS Labs publishes an official Model Context Protocol server for the Amazon S3 Tables surface (awslabs.s3-tables-mcp-server), distributed on PyPI and run locally over stdio via uvx. It exposes S3 Tables (Apache Iceberg) operations — table bucket / namespace / table management and read/write query — to MCP clients. AWS does not (at capture time) publish a hosted remote MCP server for the core S3 object REST API or the S3 Control API; the tools[] block below records the published S3 Tables server plus candidate coverage derived from the repo's OpenAPI for the object/control surfaces (status: candidate on those).

Open docs → Amazon S3 provider profile

One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.

Provider: Amazon S3 Type: Documentation link Transport: Host: awslabs.github.io

Documentation

https://awslabs.github.io/mcp/servers/s3-tables-mcp-server

Documentation link · transport

About MCP

The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.

Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.