Why Scrollport gives AI agents a small control surface instead of hundreds of tools
How apps, discover, inspect, run and wallet use progressive disclosure to give agents a growing catalog without overwhelming their context.
By Scrollport
In brief
Scrollport gives agents five stable control tools instead of loading every provider tool at once. Apps checks connected-account readiness, discover finds a suitable catalog tool, inspect loads its contract and price, run executes it, and wallet keeps spending within the human's chosen boundary.
AI agents can use hundreds of external tools, but loading hundreds of tool definitions at once is not the same as giving an agent useful choice. Every definition consumes context, competes for attention and increases the chance that the model selects the wrong operation. Scrollport takes a different approach: the agent starts with five stable control tools and loads individual catalog tools only when the job requires them.
More tool definitions do not mean more capability
A large static tool list forces an agent to compare names, schemas and provider-specific details before it has even decided what kind of work it needs to do. That approach becomes harder to manage as the catalog grows. It also couples every agent configuration to the current list of providers and endpoints.
Scrollport keeps the catalog outside the agent’s permanent context. The catalog can grow without requiring users to reinstall a larger bundle of definitions. The agent learns one stable method for finding, understanding and running the right tool.
Five control tools create a stable interface
The five control tools are apps, discover, inspect, run and wallet. They are not provider APIs. They are the small control surface an agent uses to reach the wider catalog.
- apps checks which human-connected accounts are available to the workspace and ready.
- discover searches capabilities and catalog tools using the job the agent needs to complete.
- inspect returns the selected tool’s current instructions, input contract, worked example and price.
- run executes that exact catalog tool with the supplied input.
- wallet shows the available balance and the human-controlled spending boundary.
apps does not turn account authorization into an agent action. It reports only workspace-visible readiness and, when needed, a Scrollport link for the human to open. The agent never receives the external account identity, connection id or provider credential.
This interface stays the same whether the catalog contains twenty tools or two hundred. Browse the current public tools catalog to see how categories, capabilities, literal tool identities and public providers remain distinct.
Progressive disclosure gives the agent detail when it is useful
Progressive disclosure means revealing information in stages instead of presenting every detail up front. The agent begins with its intended outcome. discover returns a short list of relevant choices. inspect then reveals the complete contract for one choice. run is only called after the agent knows the expected input and price.
The sequence reduces context noise without hiding important facts. Literal name, provider, access state, worked examples and billing units still exist; they appear at the point where they can change the decision. The platform documentationexplains the request and response contract for each control tool.
The wallet adds human control to agent execution
Tool selection and spending are related decisions. inspect provides a price estimate before execution. run can proceed beneath the human’s approval threshold or pause for approval when the expected spend is larger. Successful work is settled against one prepaid wallet; failed work releases its hold.
That design lets agents act without granting unlimited authority. The agent receives enough autonomy for routine tasks while the account owner keeps explicit control over larger spends, provider connections and wallet funding.
A growing catalog without a growing setup burden
The practical benefit is not merely a shorter tool list. It is a stable agent connection that can improve as the catalog improves. Newly published tools become discoverable through the same five controls, while unpublished or unhealthy tools stay out of public discovery.
This is a managed catalog design, not a generic proxy for arbitrary MCP servers. Read the MCP gateway comparison if you are choosing between operating a gateway, connecting servers directly or using a managed catalog. To try Scrollport, follow the quick-start guide or give your agent the setup instructions at scrollport.com/start.