Tag
Model Context Protocol
Model Context Protocol (MCP) is a standard way for AI assistants to connect to tools and data sources, across local, HTTP, and WebSocket transports with credential handling. It matters for browser sessions, governed customer data, trading, and BI integrations.
6 articles
Microsoft Agent Framework Adds MCP Tool Options
Microsoft’s Agent Framework now supports MCP over stdio, HTTP, and WebSocket, with runtime headers and tighter credential handling.
Zocks Brings MCP to ChatGPT and Claude
Zocks is rolling out MCP access for ChatGPT and Claude, aiming to cut copy-paste workflows and keep advisor client data governed.
Preset MCP adds enterprise controls to Superset
Preset wraps Apache Superset MCP with OAuth 2.0, workspace isolation, Chatbot, and Kubernetes deployment for production use.
Supabase MCP lets AI query your projects
Supabase’s MCP server connects AI tools to projects, databases, logs, and Edge Functions, with read-only mode and project scoping.
MCP Explained: From Prompts to Production
MCP lets AI apps request data, tools, and confirmations with tighter control. Zoho breaks down how it moves assistants into production workflows.
MCP Standard in 2026: Integrating AI Tools
MCP in 2026: how teams adopt Model Context Protocol for AI tool integration, ensure safe rollouts, and connect hosts with servers.