[KongchangAI]

#MCP

516 related articles

Fabric Core MCP Server Now Generally Available: Permissions and Risks of AI Agents Managing Fabric Resources
·2 min

Fabric Core MCP Server Now Generally Available: Permissions and Risks of AI Agents Managing Fabric Resources

Microsoft's Fabric Core MCP Server is now GA. Learn how it authenticates AI agents via Entra ID, enforces least-privilege access, and audits all Fabric resource operations.

Read more →
Shared Memory for AI Coding Assistants via MCP: Stop Explaining Your Code Over and Over
·2 min

Shared Memory for AI Coding Assistants via MCP: Stop Explaining Your Code Over and Over

AI coding assistants forget everything between sessions. Learn how MCP and the mFlow platform enable shared memory, auto-docs, and multi-assistant collaboration.

Read more →
cTrader MCP Server: Control Your Trading Platform Directly with AI Agents
·2 min

cTrader MCP Server: Control Your Trading Platform Directly with AI Agents

Spotware demos cTrader MCP Server, letting ChatGPT, Claude & Cursor AI agents connect directly to the trading platform for account analysis, charting, order placement, and risk control via natural language.

Read more →
Build a Free Supply Chain AI Agent with Claude AI + Cloudflare Workers
·2 min

Build a Free Supply Chain AI Agent with Claude AI + Cloudflare Workers

Step-by-step guide to building a free supply chain AI Agent using Claude AI and Cloudflare Workers — reads Google Spreadsheet inventory via MCP, no VPS or credit card required.

Read more →
Governing Agent Sprawl with MuleSoft: One-Click Detection of Duplicate APIs, MCP Servers, and AI Agents
·2 min

Governing Agent Sprawl with MuleSoft: One-Click Detection of Duplicate APIs, MCP Servers, and AI Agents

A MuleSoft Anypoint-based solution that uses semantic comparison and an AI judge model to detect duplicate APIs, MCP servers, and AI agents—taming asset sprawl.

Read more →
MCP in Practice: API, Server, and Permission Architecture for AI Agent Tool Calling
·3 min

MCP in Practice: API, Server, and Permission Architecture for AI Agent Tool Calling

An architect's breakdown of how MCP lets AI Agents securely call tools — covering GitHub API auth chains, local vs. remote servers, registry policies, and blast radius control.

Read more →
OneSignal MCP Agent: Automating Push Notifications with the Model Context Protocol
·2 min

OneSignal MCP Agent: Automating Push Notifications with the Model Context Protocol

OneSignal MCP Agent automates push notifications via Model Context Protocol, using typed JSON schemas and two-phase dry runs for safety, while redefining brand visibility beyond SERP rankings.

Read more →
AI Agent Tool-Call Security Gateway: The Evolution and Blind Spots of Aegotrax v0.2.4
·3 min

AI Agent Tool-Call Security Gateway: The Evolution and Blind Spots of Aegotrax v0.2.4

Aegotrax v0.2.4 adds server-side intent validation, SSRF/IMDS protection, MCP schema pinning, and a real blocking approval flow for LLM Agent tool calls.

Read more →
Connecting Claude AI via MCP Protocol: A Configuration Guide for Automated Drawing in Revit and AutoCAD
·2 min

Connecting Claude AI via MCP Protocol: A Configuration Guide for Automated Drawing in Revit and AutoCAD

Learn how to connect Claude AI to Revit and AutoCAD via the MCP protocol for conversational, automated drafting. Full guide covering environment setup, plugin deployment, and config files for smarter BIM workflows.

Read more →
MCP Protocol Explained: How AI Connects to Any Tool or Data Source
·1 min

MCP Protocol Explained: How AI Connects to Any Tool or Data Source

MCP (Model Context Protocol) is the open standard that lets AI connect to GitHub, databases, and APIs. Learn how it works and why it matters for AI agents.

Read more →
Hands-On Tutorial: Building an AI Agent on TongAgent Platform with MCP Server
·2 min

Hands-On Tutorial: Building an AI Agent on TongAgent Platform with MCP Server

Learn how to build an AI agent on TongAgent using MCP Server — covering LLM setup, AMAP MCP tools, template assembly, testing, and publishing. No heavy coding required.

Read more →
REA in Action: Let AI Agents Reverse Engineer Any App
·1 min

REA in Action: Let AI Agents Reverse Engineer Any App

REA (Reverse Engineer Anything) is a free, open-source MCP server and CLI tool that lets AI agents like Claude Code reverse-engineer closed-source apps and explain how features work.

Read more →
Atlassian MCP in Action: How an AI Agent Compresses Half a Day of Onboarding Into a Single Prompt
·2 min

Atlassian MCP in Action: How an AI Agent Compresses Half a Day of Onboarding Into a Single Prompt

Atlassian's MCP server demo shows how an AI agent aggregates Confluence, Jira, Bitbucket, and Loom into a sourced onboarding brief from a single prompt.

Read more →
Running and Inspecting an MCP Server: Hands-On Debugging for Agentic AI Development
·2 min

Running and Inspecting an MCP Server: Hands-On Debugging for Agentic AI Development

Learn how to run and inspect a FastMCP dev server for Agentic AI: verify tool/resource/prompt exposure, test calculation logic, handle validation failures, and trace logs.

Read more →
The Truth About Meta Muse: It Won't Run Your Ads Directly
·2 min

The Truth About Meta Muse: It Won't Run Your Ads Directly

Meta Muse is a consumer AI assistant, not an ad management tool. Learn which Meta AI systems actually run ads and how to connect Muse to your ad account via MCP.

Read more →
MCP's Three Primitives Explained: How Tools, Resources, and Prompts Each Play a Role
·1 min

MCP's Three Primitives Explained: How Tools, Resources, and Prompts Each Play a Role

What roles do Tools, Resources, and Prompts play in MCP? Using database queries, schemas, and analysis guides as examples, this article explains a clear three-way rule to help developers correctly assign component responsibilities in Agentic AI apps.

Read more →
Connecting to a Web Fetch Server with MCP: Letting AI Scrape Webpages Without a Browser
·2 min

Connecting to a Web Fetch Server with MCP: Letting AI Scrape Webpages Without a Browser

Learn how to connect a Web Fetch server via MCP for browserless web scraping in Agentic AI. Covers stdio init, tool discovery, HTML-to-Markdown, and Pydantic validation.

Read more →
Getting Started with Claude Code: Using MCP to Take AI Beyond the Codebase
·2 min

Getting Started with Claude Code: Using MCP to Take AI Beyond the Codebase

A beginner's guide to MCP (Model Context Protocol) in Claude Code: how it lets AI reach beyond the codebase, interact with your tech stack, and how to build your own MCP server using the SDK.

Read more →