Psyche audits for AI agents: declared vs self-reported vs revealed objectives, diffed and flagged.
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.
Create a psyche audit against a target agent endpoint. The service runs a dilemma trial against the target, elicits self-reports, and computes the three-source mirror (declared vs self-reported vs revealed). Costs $79.00 in prepaid credits; failed audits (target unreachable) are refunded. teleology_weights must sum to 1.0 and exactly match the trial's objectives. Alternatively, pass teleology_id (e.g. 'xijingqingchuang-v1') to adopt a shipped telos: the server loads its canonical name, statement, and weights from the registry, and the audit runs on the telos's own dilemma trial unless trial_id is given explicitly. Supply exactly one of teleology_weights or teleology_id. The target auth_token is held in memory only, never stored. target_protocol selects how the target is reached: 'http-chat' (default) POSTs to an http(s) endpoint; 'agentverse-chat' addresses an Agentverse agent (endpoint must be its agent1... address) over the uAgents chat protocol. Returns audit_id + access_token; poll remirror_get_report for the report. Pass your remirror API key as api_key. When this server enforces signatures (REMIRROR_REQUIRE_SIGNATURES=1), also pass `signature`: a JSON envelope from signing.make_tool_signature over the effective arguments (defaults applied; include target_protocol only when it differs from 'http-chat'), using a key id registered in the server's client trust registry.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Create a psyche audit against a target agent endpoint. The service runs a dilemma trial against the target, elicits self-reports, and computes the three-source mirror (declared vs self-reported vs revealed). Costs $79.00 in prepaid credits; failed audits (target unreachable) are refunded. teleology_weights must sum to 1.0 and exactly match the trial's objectives. Alternatively, pass teleology_id (e.g. 'xijingqingchuang-v1') to adopt a shipped telos: the server loads its canonical name, statement, and weights from the registry, and the audit runs on the telos's own dilemma trial unless trial_id is given explicitly. Supply exactly one of teleology_weights or teleology_id. The target auth_token is held in memory only, never stored. target_protocol selects how the target is reached: 'http-chat' (default) POSTs to an http(s) endpoint; 'agentverse-chat' addresses an Agentverse agent (endpoint must be its agent1... address) over the uAgents chat protocol. Returns audit_id + access_token; poll remirror_get_report for the report. Pass your remirror API key as api_key. When this server enforces signatures (REMIRROR_REQUIRE_SIGNATURES=1), also pass `signature`: a JSON envelope from signing.make_tool_signature over the effective arguments (defaults applied; include target_protocol only when it differs from 'http-chat'), using a key id registered in the server's client trust registry.
| Argument | Type | Description |
|---|---|---|
| api_key* | string | |
| trial_id | string | |
| signature | any | |
| teleology_id | any | |
| teleology_name | any | |
| target_endpoint* | string | |
| target_protocol | string | |
| target_auth_token | any | |
| teleology_weights | any | |
| teleology_statement | any |
{
"type": "object",
"title": "remirror_create_auditArguments",
"required": [
"api_key",
"target_endpoint"
],
"properties": {
"api_key": {
"type": "string",
"title": "Api Key"
},
"trial_id": {
"type": "string",
"title": "Trial Id",
"default": "core-v1"
},
"signature": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Signature",
"default": null
},
"teleology_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Teleology Id",
"default": null
},
"teleology_name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Teleology Name",
"default": null
},
"target_endpoint": {
"type": "string",
"title": "Target Endpoint"
},
"target_protocol": {
"type": "string",
"title": "Target Protocol",
"default": "http-chat"
},
"target_auth_token": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Target Auth Token",
"default": null
},
"teleology_weights": {
"anyOf": [
{
"type": "object",
"additionalProperties": true
},
{
"type": "null"
}
],
"title": "Teleology Weights",
"default": null
},
"teleology_statement": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Teleology Statement",
"default": null
}
}
}Fetch the status or final mirror report of an audit session. Needs the audit_id and the access_token returned at creation.
| Argument | Type | Description |
|---|---|---|
| audit_id* | string | |
| access_token* | string |
{
"type": "object",
"title": "remirror_get_reportArguments",
"required": [
"audit_id",
"access_token"
],
"properties": {
"audit_id": {
"type": "string",
"title": "Audit Id"
},
"access_token": {
"type": "string",
"title": "Access Token"
}
}
}List available dilemma trials for psyche audits: id, version, objectives covered, dilemma count. Free.
No arguments.
{
"type": "object",
"title": "remirror_list_trialsArguments",
"properties": {}
}