AI Protocols & Standards

A2A (Agent-to-Agent Protocol) is an open standard that enables AI agents to discover, communicate, and collaborate autonomously across different platforms and vendors.

AGENTS.md is an open, plain-Markdown file placed in a code repository that gives AI coding agents project-specific instructions such as build and test commands, code style and conventions.

The Agentic AI Foundation (AAIF) is a Linux Foundation directed fund, launched in December 2025, that provides neutral, open governance for agentic AI projects such as MCP, goose and AGENTS.md.

A plain-text file placed at a website's root directory that serves as an instruction manual for large language models, guiding AI systems toward your most important and authoritative content.

An open standard, introduced by Anthropic in November 2024 and now hosted by the Linux Foundation's Agentic AI Foundation, that connects AI applications to external data sources, tools and APIs.

An MCP Client is a component that enables AI models to securely connect to external marketing tools and data sources through the Model Context Protocol standard.

A centralized infrastructure layer that acts as a secure intermediary between AI agents and Model Context Protocol (MCP) servers, providing unified access to multiple data sources and tools.

MCP Server (Model Context Protocol Server) is a specialized connector that enables AI models to securely access and interact with external marketing tools and data sources in real-time.

OAuth for Agents is an authorization framework enabling AI-powered marketing tools to securely access social media platforms using tokens instead of passwords, allowing automated posting, analytics, and campaign management.

A cloud-based service that enables AI language models to connect with business applications over HTTP, allowing seamless data exchange and automated workflows for social media marketing teams without local installation requirements.

An LLM API feature that constrains a model's response to a developer-supplied JSON Schema, so the output is valid, machine-readable JSON with the required fields and allowed values.

A tool schema is the structured definition of a tool an AI model can call: its name, a natural-language description, and a JSON Schema for its input parameters, optionally with an output schema.