Model proof-of-work policy and latency for AI agents. $1 USDC rehearsal; no runtime protection.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Free scope and price discovery.
This tool takes no arguments.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Free scope and price discovery.
No arguments.
{
"type": "object",
"title": "describe_agentArguments",
"properties": {}
}$1 bounded policy rehearsal. Returns a model and local hash measurement. Does not activate endpoint protection or establish energy savings.
| Argument | Type | Description |
|---|---|---|
| backend_cost_ms* | integer | |
| client_p95_budget_ms* | integer | |
| client_hashes_per_second* | integer | |
| peak_requests_per_second* | integer |
{
"type": "object",
"title": "rehearse_defenseArguments",
"required": [
"client_hashes_per_second",
"client_p95_budget_ms",
"backend_cost_ms",
"peak_requests_per_second"
],
"properties": {
"backend_cost_ms": {
"type": "integer",
"title": "Backend Cost Ms"
},
"client_p95_budget_ms": {
"type": "integer",
"title": "Client P95 Budget Ms"
},
"client_hashes_per_second": {
"type": "integer",
"title": "Client Hashes Per Second"
},
"peak_requests_per_second": {
"type": "integer",
"title": "Peak Requests Per Second"
}
}
}