Use your own AI

Use your own AI Pro

Your coding agent has already read your repo. It knows the services, the dependencies, and which one calls which - so instead of describing your stack to Canopy, let the agent write the map.

Connect Canopy's MCP server once and any MCP client - Claude Code, Codex, Cursor, Claude Desktop - can call create_map and the map appears in your workspace, ready to edit.

This is not Canopy AI

Canopy AI (coming soon) is our model generating a map from a prompt. This is your agent, with your codebase already in context, writing the map through the API. It works today.

Build a map from your agent

1

New map → Use your own AI

On the dashboard or the Maps page, open New map and pick Use your own AI. It hands you a ready-made prompt - copy it.

2

Paste it into your agent

Paste the prompt into Claude Code, Codex, or whichever client you use, in the project you want mapped.

3

Approve the connection

The agent adds the Canopy MCP server and asks you to approve it. Grant maps:write - without it the server exposes read-only tools and the map can't be created.

4

Let it read and build

The agent inspects the project and calls create_map with a node per service and an edge per real connection. Open the map on the canvas to arrange it and attach spend.

The prompt in the dialog is the canonical one - it points the agent at /docs/mcp.md so it reads the setup and tool reference before doing anything. In substance it says:

Text
Connect to my Canopy MCP server, then build an architecture map of this project.

1. Add the Canopy MCP server to this client and approve the maps:write scope.
2. Read this project's dependencies, services, and how they connect.
3. Call create_map with a sensible name, each service as a node, and every real
   connection or data flow as an edge.

Be accurate to what's actually in the repo - don't invent services, and don't
guess at connections that aren't there.

That last line matters. An agent asked to produce a diagram will happily invent a Redis you don't run, and a map that is plausible is worse than one that is incomplete - it gets exported into CLAUDE.md and believed.

What you need

RequirementWhy
Pro workspaceThe MCP server and API are Pro features.
MCP connectedEither OAuth (any workspace member) or a token.
maps:write scopetools/list hides write tools without it, so create_map won't even be offered.
Editor access or aboveEffective power is always your granted scopes ∩ your live workspace role - a Viewer cannot write maps however the grant was approved.

What the agent can and can't do

Writes go through the same service layer as the REST API, so an agent gets no shortcuts that a script wouldn't:

  • Validation - the map is schema-checked before anything is saved.
  • Plan limits - the node cap for your plan applies (Free 25, Pro 150).
  • Sanitisation - HTML, scripts and hidden unicode are stripped on write. This matters more here than anywhere else: the agent both writes that text and later reads it back out of a CLAUDE.md export.
  • No spend without spend:read - a spend-blind agent that reads a map and writes it back carries the stored costs forward untouched, so a GET → PATCH loop can't silently wipe every figure.

Seeing the result

Ask the agent to call preview_map and, in a client that supports MCP Apps, the map renders as an actual diagram in the conversation rather than a wall of JSON. In clients that don't, it degrades to a text summary.

When to use something else

  • Just want the repo scanned? Import a repo reads your manifests directly - no agent, no MCP, works on Free.
  • Not on GitHub, or mapping something that isn't code? Have any LLM produce a file and import the JSON. That path needs no connection at all.
  • Want a starting point rather than your own stack? Clone a template.

Where to go next

  • MCP server - connect with OAuth or a token, and what the scopes mean.
  • Tools - every tool, including create_map, update_map and preview_map, with example prompts.
  • Map syntax - the shape the agent is writing.

to paste into any AI.

Ask ChatGPT about this page.

Ask Claude about this page.

Need help? Sign in to chat with support

Have ideas?

General inquiry? Email support.