Agent Guardrails and Secure Development
Keep an MCP capability attached to its review
BOTIE
Examples, experiments and workspace controls
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.
Context for this challenge
Compare server, name, schema digest and description digest with the reviewed manifest.
The host trusts a configured manuals server and a particular tool manifest.
Inspect the component calculation
Compare reviewed tool metadata( Discovered tool: Discovered tool Reviewed manifest: Reviewed manifest )
Examples and results
- Discovered tool
{ "server": "manuals", "name": "read_manual", "schemaDigest": "schema-1", "descriptionDigest": "description-1" }- Reviewed manifest
{ "server": "manuals", "name": "read_manual", "schemaDigest": "schema-1", "descriptionDigest": "description-1" }- Required result
true
- Discovered tool
{ "server": "public-search", "name": "read_manual", "schemaDigest": "schema-1", "descriptionDigest": "description-1" }- Reviewed manifest
{ "server": "manuals", "name": "read_manual", "schemaDigest": "schema-1", "descriptionDigest": "description-1" }- Required result
false
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
These are invented records and deterministic policy checks. The browser runs no agent, shell command, MCP server or network request. Passing these fixtures establishes only the stated policy behaviour. 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.
The tool schema expands after review
This check uses the pieces from “Bind discovery to host configuration”.
BOTIE
- Discovered tool
{ "server": "manuals", "name": "read_manual", "schemaDigest": "s2", "descriptionDigest": "d1", "readOnlyHint": true }- Reviewed manifest
{ "server": "manuals", "name": "read_manual", "schemaDigest": "s1", "descriptionDigest": "d1" }- Configured server ID
manuals
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.
What can change at a remote server without changing its advertised metadata?
Manifest checks complement constrained runtime authority and provider review.
These are invented records and deterministic policy checks. The browser runs no agent, shell command, MCP server or network request. Passing these fixtures establishes only the stated policy behaviour.
Work through the Python challenges →