Articles tagged "MCP"

**[DeepWiki (deepwiki.com)](https://deepwiki.com/) is an AI documentation tool from [Cognition Labs](https://www.cognition-labs.com/) — the [Devin](../columns/claude-fable-5-return-devin-cursor-2026-07) team**. **Replace `github.com` with `deepwiki.com` in any public GitHub URL** and the repo becomes an interactive wiki. **Core experience**: (1) **architecture diagrams** visualizing component dependencies, (2) **file-linked summaries** describing each module / function with direct links to the source, (3) **natural-language chat** grounded in the code ("who calls this function?", "why is it designed this way?"). **50,000+ top OSS repos are pre-indexed** (MCP, LangChain, Next.js, React, [Transformers](https://huggingface.co/docs/transformers), [VSCode](https://code.visualstudio.com/), [Playwright](https://playwright.dev/), etc.). **Private-repo support**: connect your GitHub to Devin and internal repos can also be analyzed by DeepWiki, with Devin's agent using the generated wiki when planning and executing tasks. **MCP server** — an **official one for [Cursor](../columns/cursor-ios-supports-2026-07-01) / [Claude Code](https://claude.com/product/claude-code) / Claude Desktop** so coding agents can consult DeepWiki mid-task. **Tech**: Cognition Labs' Devin AI plus the Claude Agent SDK (Claude 3.7-class LLMs); **free**. **Position**: alongside [Herdr (parallel execution)](../columns/herdr-terminal-agent-multiplexer-2026-07), [Mosaic (SHARED CONTROL)](../columns/mosaic-parallel-claude-code-2026-07), [Command Code (taste-1)](../columns/commandcode-taste-1-personalized-coding-agent-2026-07), [grill-me](../columns/grill-me-agent-skill-2026-07), and [Cerebras Gemma 4](../columns/cerebras-gemma-4-31b-multimodal-inference-2026-07), it occupies the **"understanding layer"** of the **"understand × parallel × personalized × thoroughly reviewed × fast inference" late-2026 AI dev stack**, cutting new-contributor onboarding from **days to hours**. **Caveats**: LLM hallucination remains (verify load-bearing claims by clicking through citations), Cognition Labs / Devin ecosystem dependency, and data-sovereignty considerations for private-repo use.

**[Command Code](https://commandcode.ai/) is a terminal AI coding agent** whose proprietary **"taste-1" model** combines LLMs with **continuous reinforcement learning from developer behavior**. **Core differentiator**: capture coding preferences from `accept` / `reject` / `edit` actions, producing output that increasingly matches **your architectural patterns, naming conventions, and coding style**. **Key features**: (1) **continuous learning system** — preferences captured from developer decisions, (2) **multi-mode operation** — interactive CLI, headless mode, sandbox environment, (3) **built-in tools** — file ops, shell commands, grep, extended thinking, (4) **project-level skills + persistent memory across sessions**, (5) **team collaboration** — `npx taste push/pull` share skill registries within a team, (6) **design partnership mode** — 17+ operational variants, (7) **MCP server support**. **LLM coverage**: **15+ providers** including Anthropic / OpenAI / Google / DeepSeek / Qwen / MiniMax. **Pricing**: **free tier for individuals**, Pro from **$1/month** + $10 free credits (which stretches to $40-$100 depending on model), team plans with additional seats and shared skill registries. **Install**: `npm i -g command-code`. **Claimed performance**: "Code 10× faster. Reviews, 2× quicker. Bugs 5× fewer" — per-developer personalization breaking through the ceiling of generic output. **Positioning**: a direct competitor to [Claude Code](https://claude.com/product/claude-code), [Cursor](../columns/cursor-ios-supports-2026-07-01), and [Codex](../columns/openai-chatgpt-work-launch-2026-07), but with **"individual-personalization learning"** as the differentiation axis.

A comprehensive guide to the **Skills & Tools system** in Nous Research's open-source agent Hermes Agent v0.15.2 (and the [Hermes Desktop](../columns/hermes-desktop-nous-research-2026) GUI), grounded in official docs and GitHub releases. Covers **Skills** (on-demand procedural docs) with the three-level Progressive Disclosure loading scheme starting at ~3k tokens, the `SKILL.md` format, the **skills.sh catalog that exploded from 858 to 19,932 entries in v0.15.1**, the standout new skills (`openhands`, `code-wiki`, `web-pentest`), the self-improving loop where the agent creates / patches / edits / deletes its own Skills, and **Tools** — 40+ built-ins like `web_search`, `x_search`, `terminal`, `patch`, `browser_navigate`, `vision_analyze`, `cronjob`, `memory`, `delegate_task`. Also covers MCP **client + server** support, the macOS Computer Use background execution that doesn't move the cursor or switch Spaces (5–20ms/event), and the 25+ messenger gateway (Slack / Discord / Telegram / Teams / WhatsApp / LINE / Feishu / WeCom and more). Ends with **eight category-specific combination patterns** — research, writing, data analysis, coding, customer support, social listening, internal automation, personal work — sized for Japanese enterprise practice.

**Hermes Desktop** by Nous Research is the native desktop app version of Hermes Agent, first demoed by Jensen Huang at the NVIDIA GTC keynote and now in public preview. Released under the MIT license, it supports macOS, Windows, and Linux with voice mode, cron scheduling, Computer Use, and MCP gateway integration — all sharing the same config, skills, and memory as the CLI and TUI. This column covers features, competitive positioning, and key considerations for Japanese enterprise adoption.

A primary-source read on the trend of on-device AI agents driving iOS simulators, anchored on **Argent** — Software Mansion's MCP-based iOS / Android simulator toolkit released May 8, 2026 — paired with Google's **Gemma 4 E4B** edge multimodal model. Covers Argent's actual spec (screenshot-first feedback + accessibility + profiling, MCP server implementation), Gemma 4 E4B's requirements (~2.5 GB model memory, 8 GB+ RAM, native function calling), the fact that Software Mansion's officially published Argent demo actually uses **Gemini 3.5 Flash (cloud)**, the separate on-device Gemma 4 E2B demo on an iPhone 17 Pro, and what this actually means for Japanese mobile QA and internal-app automation.

Meta launched the Meta Ads AI Connectors in open beta on April 29, 2026. Through the Model Context Protocol (MCP), advertisers can now create, manage, and analyze Facebook / Instagram campaigns directly from ChatGPT, Claude, and other MCP-compatible AI tools. This article summarizes the architecture (ads MCP server + ads CLI), the no-credential setup, supported use cases, and operational considerations — based on official sources.

A hands-on guide covering AGENTS.md authoring, priority rules, MCP integration, GitHub Actions, and team best practices. Learn how to turn Codex into a project-aware agent that works exactly the way you want.

In March 2026, software development is shifting dramatically toward Intent-Driven Development. A comprehensive guide covering vibe coding, MCP, multi-agent development, evolving developer roles, Japanese enterprise adoption, and practical implementation steps.

Claude Code by Anthropic is an agent-based development tool that autonomously codes by understanding entire codebases. Available via CLI, IDE, Desktop, and Web. Complete 2026 guide covering Opus 4.6, MCP, Agent Teams, and advanced features.

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.

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.