Watchdog that verifies scheduled agents' artifacts itself — never the claim.
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.
Report run progress — the watchdog watches progress checkpoints against the job's own wall-clock budget, never process existence. Args: run_id, note?.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Report run progress — the watchdog watches progress checkpoints against the job's own wall-clock budget, never process existence. Args: run_id, note?.
| Argument | Type | Description |
|---|---|---|
| note | string | |
| run_id* | string |
{
"type": "object",
"required": [
"run_id"
],
"properties": {
"note": {
"type": "string"
},
"run_id": {
"type": "string"
}
}
}Claim completion; the watchdog verifies the declared artifact itself (the claim is never trusted) and issues a signed, hash-chained verdict receipt. Metered check ($0.002 after the one-time 100-check trial / plan rules). Args: run_id, claimed?.
| Argument | Type | Description |
|---|---|---|
| run_id* | string | |
| claimed | string |
{
"type": "object",
"required": [
"run_id"
],
"properties": {
"run_id": {
"type": "string"
},
"claimed": {
"type": "string"
}
}
}When was this job's last VERIFIED success, and how old is it? Args: job_id.
| Argument | Type | Description |
|---|---|---|
| job_id* | string |
{
"type": "object",
"required": [
"job_id"
],
"properties": {
"job_id": {
"type": "string"
}
}
}List this operator's signed verdict receipts + receipt-chain re-verification result.
No arguments.
{
"type": "object",
"required": [],
"properties": {}
}Register a scheduled job with an outcome contract (file / URL / record, present + non-empty + fresh, optional hash/marker — or a chain contract whose stages' artifacts are the next stage's required input). Args: job_id, contract, stall_budget_s?, due_in_s?, alert via account webhook.
| Argument | Type | Description |
|---|---|---|
| job_id* | string | |
| contract* | object | |
| due_in_s | number | |
| stall_budget_s | number |
{
"type": "object",
"required": [
"job_id",
"contract"
],
"properties": {
"job_id": {
"type": "string"
},
"contract": {
"type": "object"
},
"due_in_s": {
"type": "number"
},
"stall_budget_s": {
"type": "number"
}
}
}Start a run for a job. Args: job_id.
| Argument | Type | Description |
|---|---|---|
| job_id* | string |
{
"type": "object",
"required": [
"job_id"
],
"properties": {
"job_id": {
"type": "string"
}
}
}Spot-verify a job's artifact now (independent fetch/hash/read-back by the watchdog). Metered check ($0.002 after trial / plan rules). Args: job_id.
| Argument | Type | Description |
|---|---|---|
| job_id* | string |
{
"type": "object",
"required": [
"job_id"
],
"properties": {
"job_id": {
"type": "string"
}
}
}Run the watchdog sweep: STALLED for active runs with no progress checkpoint inside the job's wall-clock budget, MISSED once per due window with no verified run. Not metered.
No arguments.
{
"type": "object",
"required": [],
"properties": {}
}