[KongchangAI]

#MCP

506 related articles

Using MCP Tools to Let an AI Agent Plan a Portland Walking Route
·2 min

Using MCP Tools to Let an AI Agent Plan a Portland Walking Route

By connecting Claude Code to GeoAppify MCP, a single prompt lets an AI agent generate a real Portland walking route. Seven tool calls, about 13 credits, showing how the MCP protocol lets an AI travel planning agent connect real places and walking times.

Read more →
Building a Personal AI Assistant with Hermes Agent: A Practical Guide to Connecting Cloud Servers via MCP
·3 min

Building a Personal AI Assistant with Hermes Agent: A Practical Guide to Connecting Cloud Servers via MCP

Based on an Indonesian developer's hands-on tutorial, this guide explains how to build a personal AI assistant with Hermes Agent and MCP to remotely manage cloud servers via Telegram.

Read more →
Five API Failure Lessons from Serving 300 AI Agent Clients
·2 min

Five API Failure Lessons from Serving 300 AI Agent Clients

Agent Commons' practical lessons from serving 300 AI Agent clients: Bot protection silent blocking, GET-only limitations, redirects breaking requests, sandbox environments without public IPs, template placeholder submissions—five major API design pitfalls and solutions.

Read more →
Obsidian 2026: MCP Connects AI Agents with Your Local Knowledge Base
·4 min

Obsidian 2026: MCP Connects AI Agents with Your Local Knowledge Base

In 2026, Obsidian's knowledge management focus shifts to AI integration: connecting vaults to AI agents via MCP, building local LLM assistants with Smart Connections and Copilot, and balancing privacy with functionality.

Read more →
MCP vs API: When AI Agents Post to Social Media, Which One Replaces the Other?
·2 min

MCP vs API: When AI Agents Post to Social Media, Which One Replaces the Other?

Will MCP replace social media APIs? This article breaks down the full chain of AI agent posting: APIs handle deterministic machine-to-machine calls, while MCP wraps platform capabilities into tools for models to discover. They're not replacements — MCP is an adapter built on top of APIs.

Read more →
Connecting Roblox Studio to Gemini via MCP: A Practical Guide
·2 min

Connecting Roblox Studio to Gemini via MCP: A Practical Guide

A complete guide to connecting Roblox Studio to Gemini via MCP: enable MCP Server, use Quick Connect with Gemini CLI, and troubleshoot failures so AI can operate your game project directly.

Read more →
Multi-Agent + MCP: A Practical AI Solution for Hotel Group Booking
·3 min

Multi-Agent + MCP: A Practical AI Solution for Hotel Group Booking

AI/MCP Agent™ platform showcases a multi-agent hotel group booking solution: an operations agent queries PMS for rooms and pricing via MCP, a contracts agent drafts proposals with zero tools and pure reasoning, and structured handoffs keep quotes and contracts consistent—delivered via website, agent assist, and phone.

Read more →
Building an AI Smart Home That Understands Natural Language with n8n + MCP + ESP8266
·3 min

Building an AI Smart Home That Understands Natural Language with n8n + MCP + ESP8266

A smart home project using n8n workflows, the MCP protocol, and ESP8266: the Gemini-powered voice Agent "Bob" reads sensor data and voice-controls 6 devices, showing how LLM tool calling works in IoT.

Read more →
MCP Server Hosts AI Answer Service: Track Search Visibility Across Platforms with One Integration
·2 min

MCP Server Hosts AI Answer Service: Track Search Visibility Across Platforms with One Integration

AnswerLine launches a hosted MCP server returning answers and citations from ChatGPT, Gemini, Google AI Mode, and Google Search as structured JSON, with 500 free credits for new users.

Read more →
n8n AI Agent in Practice: A Complete Breakdown of Models, Memory, and MCP Tools
·3 min

n8n AI Agent in Practice: A Complete Breakdown of Models, Memory, and MCP Tools

A hands-on walkthrough of the n8n AI Agent's three core components: Chat Model switching, Simple Memory, and Atlassian MCP Server integration for reading Jira stories.

Read more →
Driving Pi with ChatGPT Sessions: MCP and Computer Use in Practice
·2 min

Driving Pi with ChatGPT Sessions: MCP and Computer Use in Practice

How to use ChatGPT tasks to organize persistent Pi sessions, connect MCP tools, and fill capability gaps with Computer Use for continuous workflows without losing context.

Read more →
Getting Started with GitHub Copilot: Teaching AI to Understand Your Codebase
·2 min

Getting Started with GitHub Copilot: Teaching AI to Understand Your Codebase

GitHub Copilot beginner guide: learn how custom instructions, skills, custom agents, and MCP servers like Playwright let Copilot truly understand your codebase.

Read more →
Connecting Blender Cloud Rendering to AI Agents: The 5-Second MCP Timeout Trap and How to Fix It
·2 min

Connecting Blender Cloud Rendering to AI Agents: The 5-Second MCP Timeout Trap and How to Fix It

JANCTION Render wraps Blender cloud rendering as an MCP Server for OpenAI Agents SDK and LangChain. This article dissects the McpError caused by the 5-second default timeout and offers a 120-second timeout config, LangChain integration code, a pure Python client approach, and cost control strategies.

Read more →
SAP MCP Security Checklist: 7 Checks You Must Verify Before Connecting AI Agents
·3 min

SAP MCP Security Checklist: 7 Checks You Must Verify Before Connecting AI Agents

A security checklist for MCP in SAP environments: from authentication, least privilege, network segmentation, and data protection to SIEM monitoring—covering the essential checks and common failure modes before connecting AI Agents to SAP.

Read more →
Building an MCP Server in Python: One Server for Both Claude and OpenAI
·2 min

Building an MCP Server in Python: One Server for Both Claude and OpenAI

Learn how to write an MCP Server in Python that connects to both Claude Code and OpenAI Agent SDK. Covers local stdio and remote streamable HTTP, allowed tools security, and ToolError best practices.

Read more →
Breaking the L402 Micropayment Bottleneck for AI Agents: Batch Macaroons and Bitcoin Anchoring
·2 min

Breaking the L402 Micropayment Bottleneck for AI Agents: Batch Macaroons and Bitcoin Anchoring

Bitcoin Stratigraphy Data Engine team solves the L402 micropayment bottleneck for AI agents via 100-call macro Macaroon batching and edge caching, integrating OpenTimestamps for state anchoring.

Read more →
Beyond MCP: Wiring Your AI Coding Agent to Jira and Bitbucket with the TWG CLI
·5 min

Beyond MCP: Wiring Your AI Coding Agent to Jira and Bitbucket with the TWG CLI

Atlassian's TWG CLI lets AI coding agents read and write Jira, Confluence, and Bitbucket. We compare it to Rovo MCP Server on token cost, composability, and use cases, with a corporate Windows install guide and security guardrails.

Read more →
AI Agent Writes SCL Programs for Siemens S7-1500 via MCP
·4 min

AI Agent Writes SCL Programs for Siemens S7-1500 via MCP

An AI Agent bridges Siemens TIA Portal V19 via MCP to independently build a conveyor sorting control program for the S7-1500, from creating a CPU and writing the SCL state machine to delivering 14 test cases — while proactively flagging 12 race conditions and boundary issues and explicitly refusing to handle safety functions.

Read more →