Model Context Protocol (MCP)
An open protocol that lets AI assistants and coding agents connect to external tools and data sources through a standard interface.
MCP standardizes how an AI tool talks to the outside world. Instead of every app building custom integrations for every assistant, an app exposes an MCP server once, and any MCP-capable client, such as Claude Code, Cursor, or ChatGPT, can use it.
For feedback workflows, MCP is what turns annotations into work: a feedback tool's MCP server can hand an agent the open annotations with their context, let it fix the issues in code, and report back. The protocol was introduced by Anthropic in 2024 and has since been adopted across the major AI coding tools.
Because feedback shouldn’t be the hard part.
One link for your clients to review, one list for your team to resolve.