← All workshopsRead Connect Botie to Tools with MCP

Agents

Route the lookup to the intended manual service

BOTIE

Connect the request record to Keep the server with the tool. Return its server-qualified name.
Ready to test
0 passed · 0 failed · 2 not run

An empty floor. Start with the information your machine needs.

Received result

Your answer will arrive here.

Examples, experiments and workspace controls
Live values

Connect a tool's inputs to see what it produces. You can try a branch before connecting it to Result.

Try your own inputs

Use a copy of the example to try your own data. Keep the problem's assumptions in mind, and predict the effect of a change before checking the output. You can also add another branch to compare two ways of doing the calculation.

Start at an output arrow, then click or drag to an input. Drag empty space to pan. Delete removes a selection. Ctrl/Cmd+Z undoes a change.
Context for this challenge

Connect the request record to Keep the server with the tool. Return its server-qualified name.

Two connected services expose a read_manual tool. The host must retain their separate identities and permissions.

Inspect the component calculation
Keep the server with the tool(
  Requested server and tool: Requested server and tool
)
Examples and results
Requested server and tool
{
  "server": "maintenance",
  "tool": "read_manual"
}
Required result
maintenance/read_manual
Requested server and tool
{
  "server": "maintenance",
  "tool": "read_manual"
}
Required result
maintenance/read_manual
Try a fresh construction

This clears this draft, including its undo history. Earlier successful attempts stay recorded. Build again without opening hints to record an independent attempt.

Stuck? Inspect a worked construction

The tools below form one possible solution. You can assemble it, follow its signals, and undo that change to return to your own construction.

Assumptions and test precision

The slash names and label registry are a teaching model. Real MCP clients also negotiate capabilities, validate arguments, authenticate and handle transport and tool failures. Numerical tests allow a difference of 0.001. Lists and structures must also have the right shape.

Your last tested pieces can start the full construction. An existing draft there keeps its own pieces.

Two permitted servers still have different handlers

This check uses the pieces from “Keep the connection identity through dispatch”.

BOTIE

Both endpoints are now allowed, but the request explicitly selects archive/read_manual. Predict the handler label. Permission to call either server does not make their records interchangeable.
Requested server and tool
{
  "server": "archive",
  "tool": "read_manual"
}
Permitted server-qualified endpoints
  1. 0maintenance/read_manual
  2. 1archive/read_manual
Registered endpoint labels
{
  "maintenance/read_manual": "Current manual excerpts",
  "archive/read_manual": "Archived manual revisions"
}

Use a number, text, or an array matching the requested result. For a matrix, put each row in brackets. Saving your prediction runs your current construction on these inputs and checks the earlier examples too.

Build a construction in the workspace above first. This case will test those pieces.

Why does a successful tool-list request tell us little about whether returned manual text is reliable?

Observe discovery, routing, execution and evidence use separately. Each boundary can fail for a different reason.

The slash names and label registry are a teaching model. Real MCP clients also negotiate capabilities, validate arguments, authenticate and handle transport and tool failures.

Work through the Python challenges →
Continue the courseWhat If the Manual Starts Giving Botie Orders? →
← Ask Before Botie Creates the Inspection Job