MikeTrendsTrends right now
AI: reposAPI

search

Model Context Protocol (MCP)

Trends

  1. 1
    Figma restricts MCP access to whitelisted clients, excluding Pi●YhnWarMiddle East1881 h ago

    Figma has limited access to its Model Context Protocol server to a whitelist of approved clients, leaving out Pi. The move means developers using unapproved AI tools can no longer connect directly to Figma through MCP, and discussion online is focused on which clients made the list and what the exclusion of Pi means for AI-assisted design workflows.

  2. 2
    Google Maps Scraper MCP Released for Developers●Show HN: Google Maps Scraper MCPYhnBusiness101 h ago

    A developer has released a Google Maps Scraper built on the MCP (Model Context Protocol), allowing AI assistants to query business listings, locations and place data directly. The tool is being shared with the Hacker News community for feedback and adoption, sparking discussion among developers interested in connecting AI agents to real-world geographic and business data.

  3. 3
    Home Assistant 2026.10 Release Adds MCP Support▼Home Assistant 2026.10 Ships Tomorrow — The Open-Source Smart Home Gets Its MCP Moment✉newsTechnologySoftware1 h ago

    The next major release of Home Assistant, the popular open-source smart home platform, ships tomorrow and is billed as its 'MCP moment' — a reference to the Model Context Protocol increasingly used to connect AI assistants with external systems. The update positions the platform for deeper integration with AI agents, and observers are watching how the smart home community responds to this AI-focused step.

  4. 4
    AI agent memory gap blamed for unreliable agent complaints▼Model Context Protocol standardized how agents reach tools. It was never designed to answer what an agent remembers onceMmastodonTechnologyAI410 h ago

    Developers are pointing out that the Model Context Protocol, which standardized how AI agents connect to tools, never addressed what an agent remembers after a session ends. With MCP reportedly reaching roughly 97 million monthly SDK downloads, critics argue the protocol's lack of a memory standard is the real source of most complaints about unreliable AI agents, and calls are growing for the ecosystem to fill that gap.

Repos