remirror (返照) — psyche audits for AI agents
Psyche audits for AI agents: declared vs self-reported vs revealed objectives, diffed and flagged.
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高,可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案:
{
"mcpServers": {
"remirror": {
"url": "https://remirror.net/mcp"
}
}
}遠端端點
https://remirror.net/mcpstreamable-http它能做什麼
工具清單
工具(3)
🟢remirror_list_batteries
List available dilemma batteries for psyche audits: id, version, objectives covered, dilemma count. Free.
輸入結構描述
{
"type": "object",
"properties": {},
"title": "remirror_list_batteriesArguments"
}🟡remirror_create_audit(api_key, target_endpoint, teleology_name, teleology_statement, teleology_weights, ...)
Create a psyche audit against a target agent endpoint. The service runs a dilemma battery 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 battery'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 battery unless battery_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.
輸入結構描述
{
"type": "object",
"properties": {
"api_key": {
"title": "Api Key",
"type": "string"
},
"target_endpoint": {
"title": "Target Endpoint",
"type": "string"
},
"teleology_name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Teleology Name"
},
"teleology_statement": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Teleology Statement"
},
"teleology_weights": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Teleology Weights"
},
"teleology_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Teleology Id"
},
"battery_id": {
"default": "core-v1",
"title": "Battery Id",
"type": "string"
},
"target_auth_token": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Target Auth Token"
},
"target_protocol": {
"default": "http-chat",
"title": "Target Protocol",
"type": "string"
},
"signature": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Signature"
}
},
"required": [
"api_key",
"target_endpoint"
],
"title": "remirror_create_auditArguments"
}🟢remirror_get_report(audit_id, access_token)
Fetch the status or final mirror report of an audit session. Needs the audit_id and the access_token returned at creation.
輸入結構描述
{
"type": "object",
"properties": {
"audit_id": {
"title": "Audit Id",
"type": "string"
},
"access_token": {
"title": "Access Token",
"type": "string"
}
},
"required": [
"audit_id",
"access_token"
],
"title": "remirror_get_reportArguments"
}社群
證據