Canopy MCP server

• Registry namecom.canopy-io/docsverified in the MCP registry

The registry name sits under canopy-io.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-11-01
• Tools5
• Server calls itselfcanopy-docs
• Server version1.0.0
• Protocol version2025-06-18

On 2026-11-01 the server answered initialize and tools/list without a sign-in. First answer in 151 ms.

• Its tools do none of the product's use cases we checked: model nested org structures with inherited permissions; audit every access change across environments.
• Checked on 3 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
• What an agent can do with it0 of 2 use cases
• Answeredmeasuring3 of the 7 daily checks it takes to print a share
• Median first answer193 ms
• Space in an agent's context≈ 617 tokensthe definitions of all its tools (5), which an agent carries on every turn
• Tool definitionsA · 97 of 100
• Typed results0 of 5 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 1 of 5

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• list_surfaces

  Every left-nav page of both signed-in applications: the application, the menu path in the labels on screen, the capability that opens it, what must be selected first, and the guide that walks through it. The same data as /ai/ui-map.json.

• find_surface

  Given what someone wants to do ("rotate a webhook secret", "invite an administrator", "why can't I see Hierarchy"), return the pages where it happens, ranked, each with its menu path, the capability that opens it, and its guide.

• get_guide

  A docs page as markdown: for a dashboard guide, the menu path, the exact controls to click in order, and the reasons a control may be missing. Pass the guide URL or path from find_surface or list_surfaces, or a surface id such as…

• explain_capability

  What a capability such as env_roles.manage or billing.manage lets someone do, and which pages it opens. The answer to "why can't I see this button": a page shows only for someone holding one of its listed capabilities, and its write…

• search_api

  Search the published OpenAPI documents by words from the task or the resource. Returns method, path, operation id, and the reference page for each match. Reference pages live at /docs/api-reference/{operationId}; never guess those URLs.

• com.canopy-io/accountanswers, requires sign-inverified in the MCP registry