MCP server Pro
Canopy exposes your architecture over the Model Context Protocol - a remote MCP server at a hosted URL, no package to install. Point Claude, Cursor, or Codex at it and they read your live system as structured data: services, spend, and dependencies, on demand.
Agent
Claude · Cursor · Codex
Your maps
live architecture
Connect
Two ways to connect. The MCP server is read-only either way:
Sign in once in your browser. No token to copy, rotate, or leak.
ReadPaste a workspace token into a header. Works with every client.
ReadBoth use the same endpoint:
https://canopy.8starlabs.com/api/mcpToken vs OAuth
Prefer OAuth when your client supports it. It is scoped, read-only, and revocable without rotating a shared workspace secret. Use a workspace token for CI, headless environments, or clients that cannot complete a browser sign-in.
Tools
Once connected, agents get read-only access to these tools (each takes an
optional map id to scope to a single map):
Example prompts
Ask your MCP-connected agent questions like these. Each one is copyable:
Show me the architecture maps in this Canopy workspace, then summarize the services and connections in the most recently updated map.List every service in my Canopy workspace with its tech stack, monthly spend, and billing model.Which services cost the most each month, and which map do they belong to?Find the blast radius for the api node. What depends on it, and what does it depend on?If the database node goes down, which downstream services or workflows should I check first?Compare all maps in this workspace and tell me which one has the most services, the most connections, and the highest monthly spend.Use node ids
find_dependencies needs a node id, such as api, web, or db. If you
only know the display name, ask the agent to call list_services first and
choose the matching id.
Rate limits & usage
MCP is not a separate quota. Every tool call counts as a read against the same per-workspace rate limit and daily cap as the REST API - one budget. Calls are logged the same way and show up in Settings → API under "Usage", tagged MCP so you can tell them apart from direct API traffic.
Why MCP
Instead of a stale diagram pasted into a prompt, agents query the live map. Ask
"what breaks if the API goes down?" and the agent calls find_dependencies to
answer from real data.
Coming soon
Agent-native payments: x402 & MPP
Support for x402 and MPP (machine protocol payments) is on the roadmap, so agents can transact programmatically (e.g. pay for a template or metered access) without a human in the loop. Not available yet, this is a heads-up, not a live feature.