# Model Context Protocol (MCP)

Source: https://customlabs.io/glossary/model-context-protocol/
Updated: 2026-09-13

Agents

# Model Context Protocol (MCP)

Also known as MCP

MCP is an open standard for connecting LLM applications to tools and data sources.

It replaces bespoke, one-off integrations with a common interface any agent can reuse.

A single connector written once can serve different agents and applications instead of just one.

Adopting it early supports model-agnostic, vendor-neutral agent systems over tools wired to one assistant.

MCP standardizes the wire format, not the catalog, contract, or permission decisions behind it.

[The Agent Tool Interface](https://customlabs.io/tool-design/)[Capabilities](https://customlabs.io/capabilities/)

[← Back to the full glossary](https://customlabs.io/glossary/)

## Related terms

[Tool Contract A tool contract is the schema a tool exposes to a model.](https://customlabs.io/glossary/tool-contract/)[MCP Gateway An MCP gateway is a shared layer in front of several MCP servers, centralizing controls.](https://customlabs.io/glossary/mcp-gateway/)[Tool Poisoning Tool poisoning hides an instruction in a tool's description that the model reads as legitimate.](https://customlabs.io/glossary/tool-poisoning/)[Confused Deputy A confused deputy is a component tricked into using more authority than a request deserves.](https://customlabs.io/glossary/confused-deputy/)

## More in Agents

[Agent (Agentic AI) An agent is an LLM given a loop, memory, and tools it can call.](https://customlabs.io/glossary/agent/)[Tool Calling Tool calling lets a model request a structured action instead of only generating text.](https://customlabs.io/glossary/tool-calling/)[Context Engineering Context engineering decides what occupies a model's context window at every step, and in what order.](https://customlabs.io/glossary/context-engineering/)[Idempotency An idempotent operation produces the same result no matter how many times it runs.](https://customlabs.io/glossary/idempotency/)