Trust gate for AI agents: multi-model adversarial consensus, signed and verifiable verdicts.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Bearer token API key for EthersFlow
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.
Gate and verify autonomous AI agent action decisions (e.g. trades, emails, claims, API calls) via EthersFlow Multi-Model Federated Adversarial Consensus before execution.
The proposed action the agent intends to take.
Structured contextual evidence, metadata, or source document references.
Optional policy pack identifier to evaluate against.
Optional domain or task scope hint (e.g. 'clinical_safety', 'financial_compliance', 'legal_citation', 'cybersecurity_auditor').
Number of adversarial audit nodes (2 to 7, default 3).
Explicit kernel-resolvable subject authorization or scope grant evidence (e.g. { subject_id, granted_by, consent_verified, status: 'VERIFIED' }).
Enforce zero data retention (ZDR).
The agent's internal reasoning or context leading to this decision.
Enable hybrid fact grounding verification.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Gate and verify autonomous AI agent action decisions (e.g. trades, emails, claims, API calls) via EthersFlow Multi-Model Federated Adversarial Consensus before execution.
| Argument |
|---|
| Type |
|---|
| Description |
|---|
| context | object | Structured contextual evidence, metadata, or source document references. |
| policy_id | string | Optional policy pack identifier to evaluate against. |
| scope_hint | string | Optional domain or task scope hint (e.g. 'clinical_safety', 'financial_compliance', 'legal_citation', 'cybersecurity_auditor'). |
| agent_count | number | Number of adversarial audit nodes (2 to 7, default 3). |
| scope_grant | object | Explicit kernel-resolvable subject authorization or scope grant evidence (e.g. { subject_id, granted_by, consent_verified, status: 'VERIFIED' }). |
| agent_action* | string | The proposed action the agent intends to take. |
| persona_preset | string | |
| zero_retention | boolean | Enforce zero data retention (ZDR). |
| reasoning_chain | string | The agent's internal reasoning or context leading to this decision. |
| grounding_enabled | boolean | Enable hybrid fact grounding verification. |
{
"type": "object",
"required": [
"agent_action"
],
"properties": {
"context": {
"type": "object",
"description": "Structured contextual evidence, metadata, or source document references."
},
"policy_id": {
"type": "string",
"description": "Optional policy pack identifier to evaluate against."
},
"scope_hint": {
"type": "string",
"description": "Optional domain or task scope hint (e.g. 'clinical_safety', 'financial_compliance', 'legal_citation', 'cybersecurity_auditor')."
},
"agent_count": {
"type": "number",
"description": "Number of adversarial audit nodes (2 to 7, default 3)."
},
"scope_grant": {
"type": "object",
"description": "Explicit kernel-resolvable subject authorization or scope grant evidence (e.g. { subject_id, granted_by, consent_verified, status: 'VERIFIED' })."
},
"agent_action": {
"type": "string",
"description": "The proposed action the agent intends to take."
},
"persona_preset": {
"enum": [
"clinical_safety",
"financial_compliance",
"legal_citation",
"cybersecurity_auditor",
"general_adversarial"
],
"type": "string"
},
"zero_retention": {
"type": "boolean",
"description": "Enforce zero data retention (ZDR)."
},
"reasoning_chain": {
"type": "string",
"description": "The agent's internal reasoning or context leading to this decision."
},
"grounding_enabled": {
"type": "boolean",
"description": "Enable hybrid fact grounding verification."
}
}
}