AI Agent2026-05-17
MCP (Model Context Protocol)
Also known as: MCP / Model Context Protocol / モデルコンテキストプロトコル
Anthropic's open protocol (Nov 2024) connecting AI agents to external tools — the LSP for AI, with a clear host/server separation.
Overview
MCP connects AI hosts (e.g. Claude Code) to MCP servers (GitHub, Slack, databases) via standardised JSON-RPC. Define tools once on the server; any compliant host can call them.
By 2026 most major coding tools support MCP. See MCP integration guide.
Related Columns
Software Development
Claude Code MCP Integration Guide — Accelerate Development with External Tool Integration
Model Context Protocol (MCP) is an open standard connecting Claude Code with external tools and data sources. Practical guide covering GitHub, Slack, Notion, AWS, GCP integration, custom MCP server creation, Hooks integration, and enterprise best practices for Tokyo development teams.
AI
Why DocDD (Document-Driven Development) Matters More in the Vibe Coding Era — A Practical Guide to Avoiding AI Rework Hell [2026]
In the vibe coding era where AI rapidly generates code from natural language, the biggest risk is producing code that runs but doesn't solve the real problem. This article explains how combining DocDD (Document-Driven Development) with AI coding tools minimizes rework while preserving both quality and speed. Built on the DocDD concept introduced by okikusan on Zenn (July 2025), with additional notes on our AI-brainstorm-to-plan.md workflow.
Software Development
OpenClaw Plugin & MCP Integration Guide: Connecting AI Agents with External Services
Learn how to integrate OpenClaw with external services like GitHub, Notion, Google Drive, and databases using MCP (Model Context Protocol). This practical guide covers plugin setup, custom MCP server development, and security best practices for AI agent integrations.
AI
What Is Claude for Financial Services? Anthropic's Reference Agents and MCP Connectors for Finance
Claude for Financial Services is Anthropic's official, free reference repository of 10 named workflow agents, 9 vertical skill plugins, and 12 MCP data connectors for investment banking, equity research, private equity, and wealth management. Updated Sep 2026.
AI
What Is Hindsight? A Guide to Vectorize's Open-Source Agent Memory Layer That Learns Over Time
Hindsight is an open-source (MIT) agent memory system by Vectorize built to create agents that learn over time, not just recall chat history — it hits state-of-the-art scores on the LongMemEval benchmark. Updated Sep 2026.
AI
Ollaya: Run Jev-Style Decision Models Locally, Ollama-Style
Ollaya is an open-source local runtime for decision models: state and typed questions in, calibrated probabilities out in ms, via Ollama-style pull/run/serve.
Feel free to contact us
Contact Us