---
title: "Model Context Protocol (MCP)"
type: "glossary-term"
category: "AI & LLMs"
canonical_url: "https://www.graphcanon.com/glossary/ai-and-llms/model-context-protocol"
updated: "2026-07-09"
---

# Model Context Protocol (MCP)

_Also known as: MCP_

**MCP is an open protocol that lets AI agents discover and call external tools and data sources over a standard interface, instead of every app inventing its own.**

The **Model Context Protocol (MCP)** is an open standard for connecting AI agents to tools and data. A server exposes a set of typed tools; any MCP-capable client (Cursor, Claude, Windsurf, and others) can discover and call them without custom glue code.

MCP turns "give the model a tool" into a portable, reusable contract, which is why it has become a common integration point for agent tooling.

## In GraphCanon

GraphCanon runs a read-only MCP server so agents can search the graph, resolve tools by constraints, and read trust reports directly - no scraping. Setup lives in the MCP docs.

## See also

- [MCP server docs](/docs/mcp)
- [API for agents](/api)

## Related terms

- [AI agent](/glossary/ai-and-llms/ai-agent.md)
- [ai-catalog.json](/glossary/discovery-for-agents/ai-catalog.md)

[AI & LLMs](/glossary/ai-and-llms.md) · [All glossary terms](/glossary.md)

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon`](/api/graphcanon)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_