Most products that add an AI integration add a surface. A handful of endpoints get wrapped, the demo works, and then the product moves on and the integration quietly falls a year behind. The tell is always the same: you can do a thing in the app that you cannot do through the API, and nobody can tell you which things those are.
We wrote the rule the other way around. Every capability the panel has is a tool an agent can call. A feature ships on both surfaces or it does not ship.
What that actually means in the code
The important part is not the MCP server. It is that the MCP tools and the panel’s HTTP routes call the same authorization module. There is no second, looser path into your data — an agent holding your token is bound by exactly the roles you were granted, and if someone removes you from a project, the agent loses that project at the same instant you do.
That is also why every change an agent makes lands on the ticket’s activity trail under your name. It is not a separate integration acting on your behalf; it is you, with a different client.
What it costs
Parity is a tax on every feature. Adding a settings toggle means adding the tool that sets it, and the tool has to enforce the same permission checks and produce the same audit event. A feature is not done when the screen works.
We think that tax is the point. The alternative — an API that covers the parts somebody remembered — is the thing that makes agents useless for real work, because the moment the model hits a gap it has to hand the task back to you.
Connecting
Create a personal access token in Personal settings → API & MCP, then:
claude mcp add -t http notarus https://<your-domain>/mcp \
-H "Authorization: Bearer pat_…"Ask it whoami on notarus to confirm the connection, then try something real: “list my tickets
in Received and take the newest one.” That is list_tickets followed by assign_ticket("me"),
and the ticket’s history will show you did it.
The server is also self-documenting. initialize returns orientation instructions, and the
get_documentation tool returns the entire manual — an agent can learn the whole system without
leaving MCP, which is a good deal more reliable than hoping it guessed the shape of your API.