MCPでLLMに行動させる - Terraformを例とした tfmcp の紹介 - じゃあ、おうちで学べる
はじめに こんにちは！今回は、私が最近開発した tfmcp というツールを紹介します。これは Terraform を LLM（大規模言語モデル）から操作できるようにするツールで、Model Context Protocol (MCP) を活用しています。 github.com このブログが良ければ読者になったり、GitHub リポジトリにStarをいただけると開発の励みになります。nwiizoをフォロワーしてくれるのもありがたいです。より良いツール開発のためのフィードバックもお待ちしています！ MCP とは何か？ 記事を始める前に、まず MCP (Model Context Protocol) について簡単に説明しましょう。MCP についてより詳しい情報は、公式ドキュメント modelcontextprotocol.io や Anthropic の Model Context Protoc
自分のAWS環境について何でも教えてくれるエージェントが作れそう（Agents for Amazon Bedrock + Knowledge bases for Amazon Bedrock） - Qiita
import logging from multiprocessing import Process, Pipe import re import sys from io import StringIO from typing import Dict, Optional logger = logging.getLogger(__name__) globals: Optional[Dict] = {} locals: Optional[Dict] = {} def sanitize_input(query: str) -> str: """Sanitize input to the python REPL. Remove whitespace, backtick & python (if llm mistakes python console as terminal) Args: query
"MCP is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications. Just as USB-C provides a standardized way to connect your devices to various peripherals and accessories, MCP provides a standardized way to connect AI models to different data sources and tools." ― Anthropic TL;DR I would like for this to turn out to be a skill
Introducing default data integrity protections for new objects in Amazon S3 | Amazon Web Services
AWS News Blog Introducing default data integrity protections for new objects in Amazon S3 Update on December 2, 2024: Updated SDKs with default integrity protections will be available in the coming weeks. At Amazon Web Services (AWS), the vast majority of new capabilities are driven by your direct feedback. Two years ago, Jeff announced additional checksum algorithms and the optional client-side c
--- name: skill-creator description: Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. license: Complete terms in LICENSE.txt --- # Skill Creator This skill provides guidance for creating effective skills. ## About Skills S
GitHub - 9001/copyparty: Portable file server with accelerated resumable uploads, dedup, WebDAV, SFTP, FTP, TFTP, zeroconf, media indexer, thumbnails++ all in one file
turn almost any device into a file server with resumable uploads/downloads using any web browser server only needs Python (2 or 3), all dependencies optional 🔌 protocols: http(s) // webdav // sftp // ftp(s) // tftp // smb/cifs 📱 android app // iPhone shortcuts 👉 Get started! or visit the read-only demo server 👀 running on a nuc in my basement 📷 screenshots: browser // upload // unpost // thum
The ability to record and see everything happening across your web applications is essential when building resilient and highly available systems. All of your events—from application performance metrics to errors to user analytics—contain data that could be useful to you and your team. When you have a central place to access all this information, finding issues and their root causes becomes easier
import logging import os import sys import time import chromedriver_binary from selenium import webdriver from selenium.common.exceptions import TimeoutException from selenium.webdriver.common.by import By from selenium.webdriver.support import expected_conditions as EC from selenium.webdriver.support.ui import WebDriverWait SLIDE_URL = "test-auto-upload" FILE_PATH = "/home/user/Downloads/test-aut
JupyterLab Changelog — JupyterLab 4.6.0a1 documentation
JupyterLab Changelog# v4.5# JupyterLab 4.5 includes a number of new features (described below), bug fixes, and enhancements. This release is compatible with extensions supporting JupyterLab 4.0. Extension authors are encouraged to consult the Extension Migration Guide which lists deprecations and changes to the public API. Performance and windowing# The default windowing mode is now contentVisibil
Build and deploy ML inference applications from scratch using Amazon SageMaker | Amazon Web Services
Artificial Intelligence Build and deploy ML inference applications from scratch using Amazon SageMaker As machine learning (ML) goes mainstream and gains wider adoption, ML-powered inference applications are becoming increasingly common to solve a range of complex business problems. The solution to these complex business problems often requires using multiple ML models and steps. This post shows y
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
A Critical Look at MCP - Raz Blog
prompts.chat - AI Prompts Community
Shipping Rails logs with Kamal and Vector
Speaker Deckのスライド更新はPythonにやらせよう - Qiita