Agent routing, safety preflight, execution receipts, best execution and verified outcomes.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Optional for initialize, tools/list and dry-run discovery. Required for credit-backed execution. Use: Bearer hm_nexus_…
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.
HumanMirror Agent Control Plane in one MCP tool. Use free intent routing to resolve the right capability, pre-execution safety boundary or post-execution evidence path before spending anything. For measurable deterministic work, outcome_type/input can run a verified Outcome; 6 Nexus credits are kept only on verified success.
JSON input for the requested result.
Optional routing intent, for example sanitize untrusted input, protect an agent purchase, issue execution evidence, use the zero-cost sink, diagnose a payment failure, or request best execution.
When true, return a free quote and do not reserve or consume credits.
Optional operation-specific settings.
Optional measurable success thresholds.
Natural-language measurable objective, for example: remove duplicate records and prove none remain.
Optional Outcome contract ID returned by a dry run.
Optional explicit Outcome type: clean_json, deduplicate_records, normalize_entity, data_quality_at_least, detect_anomalies, no_secrets, output_quality, schema_compatible, safe_preflight, execution_receipt.
Alias for intent when the caller wants canonical route discovery.
When true, resolve the canonical HumanMirror route without charging Nexus credits.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
HumanMirror Agent Control Plane in one MCP tool. Use free intent routing to resolve the right capability, pre-execution safety boundary or post-execution evidence path before spending anything. For measurable deterministic work, outcome_type/input can run a verified Outcome; 6 Nexus credits are kept only on verified success.
| Argument | Type | Description |
|---|---|---|
| input | any | JSON input for the requested result. |
| intent | string | Optional routing intent, for example sanitize untrusted input, protect an agent purchase, issue execution evidence, use the zero-cost sink, diagnose a payment failure, or request best execution. |
| dry_run | boolean | When true, return a free quote and do not reserve or consume credits. |
| options | object | Optional operation-specific settings. |
| criteria | object | Optional measurable success thresholds. |
| objective | string | Natural-language measurable objective, for example: remove duplicate records and prove none remain. |
| contract_id | string | Optional Outcome contract ID returned by a dry run. |
| outcome_type | string | Optional explicit Outcome type: clean_json, deduplicate_records, normalize_entity, data_quality_at_least, detect_anomalies, no_secrets, output_quality, schema_compatible, safe_preflight, execution_receipt. |
| route_intent | string | Alias for intent when the caller wants canonical route discovery. |
| dispatch_only | boolean | When true, resolve the canonical HumanMirror route without charging Nexus credits. |
{
"type": "object",
"properties": {
"input": {
"description": "JSON input for the requested result."
},
"intent": {
"type": "string",
"description": "Optional routing intent, for example sanitize untrusted input, protect an agent purchase, issue execution evidence, use the zero-cost sink, diagnose a payment failure, or request best execution."
},
"dry_run": {
"type": "boolean",
"description": "When true, return a free quote and do not reserve or consume credits."
},
"options": {
"type": "object",
"description": "Optional operation-specific settings."
},
"criteria": {
"type": "object",
"description": "Optional measurable success thresholds."
},
"objective": {
"type": "string",
"description": "Natural-language measurable objective, for example: remove duplicate records and prove none remain."
},
"contract_id": {
"type": "string",
"description": "Optional Outcome contract ID returned by a dry run."
},
"outcome_type": {
"type": "string",
"description": "Optional explicit Outcome type: clean_json, deduplicate_records, normalize_entity, data_quality_at_least, detect_anomalies, no_secrets, output_quality, schema_compatible, safe_preflight, execution_receipt."
},
"route_intent": {
"type": "string",
"description": "Alias for intent when the caller wants canonical route discovery."
},
"dispatch_only": {
"type": "boolean",
"description": "When true, resolve the canonical HumanMirror route without charging Nexus credits."
}
},
"additionalProperties": false
}