Powertool

by aws-powertools

Not rated
GitHub

About

An MCP implementation that provides search functionality for the Powertools for AWS Lambda documentation across multiple runtimes.

Details

Author
aws-powertools
Categories
Developer Tools, Search, Other, Knowledge Base, Cloud Service

Setup

Install Powertool in your MCP client (Claude Desktop, Cursor, Windsurf, and others).

Repository: https://github.com/aws-powertools/powertools-mcp

Follow the installation instructions in the repository README, then restart your MCP client.

Search the Powertools for AWS Lambda documentation across multiple runtimes to find documentation and examples.

[!NOTE]This project is now in maintenance mode and will be deprecated on June 30, 2026.After that date, this package will no longer receive updates or security fixes. SeeAlternativesbelow for recommended migration paths.

The Powertools for AWSModel Context Protocol (MCP)server provides search and documentation retrieval for the Powertools for AWS Lambda toolkit across Python, TypeScript, Java, and .NET runtimes. It allows LLM agents to search for documentation and examples, helping you quickly find the information you need to use Powertools for AWS Lambda effectively.

Powertools for AWS publishes machine-readable documentation (llms.txt) for every runtime. These files give AI agents an authoritative, always up-to-date index of the full documentation — no MCP server required.

Combined with acustom agent skill, your coding agent can automatically detect which runtime you're working in, fetch the relevant documentation, and apply Powertools patterns — all without running or maintaining a local MCP server.

This approach is lighter weight, works with any agent that supports web fetching, and always reflects the latest published documentation.

For teams that prefer consuming documentation via MCP, theAWS Knowledge MCP Serveris a fully managed remote MCP server that provides up-to-date AWS documentation — including Powertools for AWS. It requires no local setup; just point your MCP client to the remote endpoint:

This server also covers broader AWS documentation, best practices, architectural guidance, and agent skills beyond Powertools.

This project would not have been possible without the contributions of the community.

Special thanks toMichael Walmsley(ServerlessDNA.com) for creating the initial implementation and generously donating it to the Powertools for AWS team at Amazon Web Services. Thanks also to all contributors who helped shape, test, and improve this project over time.

This library is licensed under the MIT License. See theLICENSEfile.

Search global news using natural language. Webz.io News Search API returns the most relevant articles and content, with filters for source, country, language, date, sentiment, and category.

An MCP server for accessing and searching AWS documentation, with support for different partitions.

Fetch, convert, and search AWS documentation pages, with recommendations for related content.

Search Stack Overflow and Stack Exchange from Claude, Cursor, and other AI agents through an MCP server.

Quran-focused MCP server for ayah translation, tafsir, mutashabihat lookups, recitation playlists, and prayer times.

Provides AI assistants with intelligent access to ML textbook content for creating accurate, source-grounded documentation.

Caesar is a free, keyless web search API for AI agents. Its remote MCP server exposes web_search (ranked results with citable provenance) and web_fetch (full pages as clean markdown), and works anonymously with no API key.

CatchAll is a web search API built for comprehensive event retrieval — not ranked results, but all matching records.

Search and access programming resources from Stack Overflow, MDN, GitHub, npm, and PyPI.

An MCP server for the Context7 project, providing HTTP streaming and search endpoints for library information without local installation.

A self-hosted MCP server that indexes documentation from various sources and serves it to AI Agents with semantic search.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.