Aws S3 Explorer Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Aws S3 Explorer Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
An open-source Model Context Protocol (MCP) server built in Python that securely connects AI assistants to Amazon S3.
This server provides Large Language Models (LLMs) with the ability to list buckets, inspect dataset structures, and read file schemas directly without requiring massive data downloads. It is engineered for ML infrastructure pipelines, featuring fully asynchronous I/O and defensive error handling.
aiobotocore for non-blocking concurrent requests, ensuring the server doesn't fall over under heavy LLM workloads.FastMCP wrapper to automatically generate robust JSON schemas for the client.pytest and pytest-asyncio, integrated into a GitHub Action pipeline.This server exposes three specific primitives:
list_s3_buckets(): Lists all S3 buckets accessible by the current AWS credentials.list_s3_objects(bucket_name, prefix, max_keys): Lists objects inside a specific bucket. Limits results by default to prevent LLM context window overflow.read_s3_file_head(bucket_name, object_key, byte_limit): Reads the first few kilobytes of an S3 object to inspect its contents (e.g., CSV headers, JSON structures) without downloading the entire file.aws configure or ~/.aws/credentials)If you have uv installed, you can quickly run the server without manual installation:
uvx aws-s3-explorer-mcpInstall the package from PyPI:
pip install aws-s3-explorer-mcpYou can start the MCP server by running:
aws-s3-explorer-mcpClone the repository and install the required dependencies:
git clone https://github.com/kbates97/AWS_S3_Explorer_MCP.git
cd AWS_S3_Explorer_MCP
python -m venv venv
# Windows: .\venv\Scripts\activate
# Mac/Linux: source venv/bin/activate
pip install -r requirements.txtYou can run the server locally with:
python ./src/aws_s3_mcp/server.py~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.