Evidence-bound stopping for agents: judgment ledger, binding futility verdicts, signed receipts.
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.
Record one usefulness judgment (useful / useless / partial) for a run/source/domain and return the binding verdict (CONTINUE / STOP-SOURCE / INTEGRATE-NOW / ABSTAIN). Billed as a verdict call: one-time trial, tier allowance, or x402 $0.002.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Record one usefulness judgment (useful / useless / partial) for a run/source/domain and return the binding verdict (CONTINUE / STOP-SOURCE / INTEGRATE-NOW / ABSTAIN). Billed as a verdict call: one-time trial, tier allowance, or x402 $0.002.
| Argument | Type | Description |
|---|---|---|
| label* | string | |
| query | string | |
| domain | string | |
| run_id* | string | |
| source* | string | |
| tokens | integer |
{
"type": "object",
"required": [
"run_id",
"source",
"label"
],
"properties": {
"label": {
"type": "string"
},
"query": {
"type": "string"
},
"domain": {
"type": "string"
},
"run_id": {
"type": "string"
},
"source": {
"type": "string"
},
"tokens": {
"type": "integer"
}
}
}Mint the HMAC-signed abstention receipt when the run/source/domain verdict is ABSTAIN.
| Argument | Type | Description |
|---|---|---|
| domain | string | |
| run_id* | string | |
| source* | string |
{
"type": "object",
"required": [
"run_id",
"source"
],
"properties": {
"domain": {
"type": "string"
},
"run_id": {
"type": "string"
},
"source": {
"type": "string"
}
}
}Register a run with its alternatives and operator-registered source identities (strings or {id, aliases}) before judging.
| Argument | Type | Description |
|---|---|---|
| run_id* | string | |
| sources | array | |
| alternatives | array |
{
"type": "object",
"required": [
"run_id"
],
"properties": {
"run_id": {
"type": "string"
},
"sources": {
"type": "array"
},
"alternatives": {
"type": "array",
"items": {
"type": "string"
}
}
}
}Read the current verdict for a run/source/domain without recording a judgment.
| Argument | Type | Description |
|---|---|---|
| domain | string | |
| run_id* | string | |
| source* | string |
{
"type": "object",
"required": [
"run_id",
"source"
],
"properties": {
"domain": {
"type": "string"
},
"run_id": {
"type": "string"
},
"source": {
"type": "string"
}
}
}Verify a receipt payload {receipt, signature}; total rejection with a reason on malformed/forged input.
| Argument | Type | Description |
|---|---|---|
| receipt* | object | |
| signature* | string |
{
"type": "object",
"required": [
"receipt",
"signature"
],
"properties": {
"receipt": {
"type": "object"
},
"signature": {
"type": "string"
}
}
}Waste report for a run: tokens spent after the verdict point, per source and per domain aggregate.
| Argument | Type | Description |
|---|---|---|
| run_id* | string |
{
"type": "object",
"required": [
"run_id"
],
"properties": {
"run_id": {
"type": "string"
}
}
}