Our MCP will now respect these settings. If inference is off, it shouldn’t access your data.
Rude1 Haunted Badness. ⁂
ICYMI: We have a new "AI Preferences" setting This allows you to announce to the entire ATmosphere network what you consent to regarding AI use of your public data. Other apps can see this but ~may not~ respect the settings We built this to give you a place to set these and will 100% respect them
May 8, 2026 at 4:16 AM
Stateless MCP has recaptured my interest (and inspired mcp-explorer and datasette-mcp)
Tuesday was Stateless MCP day—the rollout of MCP 2.0, or the 2026-07-28 Model Context Protocol specification to use the more formal but less memorable name. This is the most significant …
Poison everywhere: No output from your MCP server is safe
The Model Context Protocol (MCP) is an open standard and open-source project from Anthropic that makes it quick and easy for developers to add real-world functionality — like sending emails or...
Readwise MCP Server - Readwise Docs
The Model Context Protocol (MCP) standardizes how applications provide context to Large Language Models (LLMs). The Readwise MCP was created to act as a...
Replit — Model Context Protocol (MCP): A Comprehensive Guide
Learn how Replit's Model Context Protocol (MCP) lets AI models access tools and data seamlessly using a simple, universal interface.
What is the Model Context Protocol (MCP)? - Model Context Protocol
Use this file to discover all available pages before exploring further.
What is the Model Context Protocol (MCP)? - Model Context Protocol
Use this file to discover all available pages before exploring further.
What is the Model Context Protocol (MCP)? - Model Context Protocol
Use this file to discover all available pages before exploring further.
The Creators of Model Context Protocol
Introducing the Model Context Protocol
The Model Context Protocol (MCP) is an open standard for connecting AI assistants to the systems where data lives, including content repositories, business tools, and development environments. Its aim is to help frontier models produce better, more relevant responses.
Unlinkable Inference as a User Privacy Architecture
Unlinkable inference is a technique that provably sandboxes your AI requests from each other and from your identity. We discuss its building blocks, applications, and how it fits into the broader landscape of private personal intelligence.
MCP Server Directory: 19,410+ updated daily | PulseMCP
A daily-updated directory of all Model Context Protocol (MCP) servers available on the internet. Connect your AI apps to external data sources and services.
