Skip to content

AI governance glossary

Model Context Protocol (MCP)

Model Context Protocol is an open protocol introduced by Anthropic in November 2024 for connecting AI applications to tools and data.

Why it matters

A shared protocol can simplify how AI applications connect to tools and data. Each connection still needs clear access, identity, and review boundaries.

How it works

MCP defines a way for an AI application to communicate with a server that exposes tools or data. The capabilities available depend on each server and its configuration.

How Halo approaches it

Halo’s MCP and tool gateway applies identity, policy, approval, budget, and evidence controls to supported agent tool traffic.

Put a halo around the AI your business runs.

See discovery, runtime policy, approvals, and evidence working together on your own use cases.