Concepts

This section explains the ideas behind Canopy. Read these if you want to understand what’s happening under the hood — why the tool works the way it does, what its limits are, and how to reason about it.

Pages in this section

1. What Canopy Is and Isn’t — positioning, what problem Canopy solves, how it fits alongside AI coding agents.

2. How Canopy Works — the full pipeline from repo to structured intelligence: indexing, the three data stores, MCP server, and how agents consume tools.

3. AST Parsing — why Canopy uses tree-sitter ASTs instead of regex or line-based text search, and what that means in practice.

4. MCP Protocol — what the Model Context Protocol is, how Canopy implements it, and the 21 tools organized into workflow, search, graph, health, git, and ingest categories.

5. License and Privacy — exactly what Canopy sends over the network (one weekly call), what it doesn’t (your code, queries, file paths), and the air-gapped option for classified environments.

6. Tool Catalog — all 21 MCP tools in one place with one-line descriptions and links to the Reference section.

If you’re in a hurry

• Wondering if Canopy will send your code anywhere? Read License and Privacy first.
• Evaluating Canopy for your team? Read What Canopy Is and Isn’t for an honest positioning.
• Want to know which tool to call when? Read Tool Catalog — it’s a one-page cheat sheet.