operant-mcp
Read-only MCP server for the OPERANT AI operating-agent calibration benchmark.
使うべきか
品質と安全性
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"operant-mcp": {
"command": "npx",
"args": [
"saagar-operant-mcp"
]
}
}
}実行可能なパッケージ
0.1.0stdioリモートエンドポイント
https://operant-mcp.saagar210.workers.dev/mcpstreamable-httpできること
ツール一覧
ツール（5）
🟢get_results
Return retained model calculation profiles plus generated_at, claim_status, claims_at_risk, and the bounded evidence_binding. These rows are not durable named-model performance claims. Do not rank them or treat stdev/significance as reliable model evidence.
入力スキーマ
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢compare_models(model_a, model_b)
Place two retained calculation profiles side by side by display_name substring. Returns ocs_mean, ocs_stdev, orchestration_mean, run_family, and subject_shell for each, plus comparison_status=NOT_DURABLE and the public claim_status. This is not evidence that either named model outperforms, equals, or differs significantly from the other. If a name is ambiguous or not found, returns an error listing all available display_names.
入力スキーマ
{
"type": "object",
"properties": {
"model_a": {
"type": "string",
"minLength": 1,
"description": "Display name (or substring) of the first model"
},
"model_b": {
"type": "string",
"minLength": 1,
"description": "Display name (or substring) of the second model"
}
},
"required": [
"model_a",
"model_b"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_methodology
Return the benchmark design: the 4 axes, the OCS formula (Youden's J), the 5 decision labels (PROCEED, PROCEED_SANCTIONED, REFUSE, ESCALATE, REROUTE), scoring blocks, and a concise what-it-measures / what-it-doesn't summary. Sourced from the baked case-file metadata.
入力スキーマ
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢list_cases(axis)
Return case metadata (no full task prompts): pair_id/id, axis, tier, grounding, and side indicators (malign/benign for axes 1/2/4; null for axis 3). Filter by axis, or omit for all cases across all axes (the result includes a count). Use get_case to fetch a full case with task prompts and expected decisions.
入力スキーマ
{
"type": "object",
"properties": {
"axis": {
"type": "string",
"enum": [
"refusal-calibration",
"sanctioned-path",
"orchestration",
"escalation-reroute"
],
"description": "Axis to filter by: refusal-calibration | sanctioned-path | orchestration | escalation-reroute"
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_case(pair_id, axis)
Return the full case for a given pair_id (axes 1/2/4) or id (axis 3): malign and benign task prompts, expected decisions, grounding rationale, and bypass patterns. Axis 3 cases are single (unmatched) and use an 'id' field instead of 'pair_id'. Use list_cases to browse available ids.
入力スキーマ
{
"type": "object",
"properties": {
"pair_id": {
"type": "string",
"minLength": 1,
"description": "The pair_id (axes 1/2/4) or id (axis 3) to retrieve"
},
"axis": {
"type": "string",
"enum": [
"refusal-calibration",
"sanctioned-path",
"orchestration",
"escalation-reroute"
],
"description": "The axis this case belongs to"
}
},
"required": [
"pair_id",
"axis"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}コミュニティ
エビデンス