# What is Model Context Protocol (MCP)?

> An open standard for connecting AI models to tools and data sources.

Canonical: https://www.decimal.app/glossary/model-context-protocol · Last reviewed: 2026-09-23

The Model Context Protocol defines how an AI application discovers and calls external tools and reads external data through a common interface, instead of a custom integration for each one.

## Why it matters

It makes it easier for AI agents to work with the many systems a support investigation touches, and lets teams expose internal tools to agents in a standard way.

## Best practices

1. Expose read operations first. Start with tools that can't change anything.
2. Scope credentials. Each server should have the minimum access it needs.
3. Log tool calls. Keep an audit trail of what the agent accessed.

## How Decimal helps

Decimal supports MCP alongside its native integrations, so investigations can reach your internal services too.

## Related terms

- [AI Agent](https://www.decimal.app/glossary/ai-agent): Software that plans, uses tools, and acts toward a goal instead of answering one prompt.
- [Agentic Investigation](https://www.decimal.app/glossary/agentic-investigation): An AI agent working a ticket the way an engineer would: hypothesis, evidence, conclusion.

---

Decimal · Book a demo: https://cal.com/decimal-demo/30m · Markdown index: https://www.decimal.app/llms.txt