Delivery-capacity landing governor
Meters agent-fleet acceptance capacity per operator and triages what lands.
使うべきか
品質と安全性
検出事項（2）
- LOWTool 'governor_stats' description lacks action verbgovernor_stats 内
- LOWTool 'verdict_queue' description lacks action verbverdict_queue 内
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": {
"delivery-capacity-landing-governor": {
"url": "https://textforagents.com/products/delivery-capacity-landing-governor/mcp"
}
}
}リモートエンドポイント
https://textforagents.com/products/delivery-capacity-landing-governor/mcpstreamable-httpできること
ツール一覧
ツール（7）
⚪governor_record(project_id, operator, surface, units)
Record a capacity event (surface merge|checkout|ci_minutes|submission, units) for an operator on a project. Requires an active Meter + Verdicts subscription. Project cap checked before per-operator budget; denied events consume no budget.
入力スキーマ
{
"type": "object",
"properties": {
"project_id": {
"type": "string"
},
"operator": {
"type": "string"
},
"surface": {
"type": "string"
},
"units": {
"type": "number"
}
},
"required": [
"project_id",
"operator",
"surface",
"units"
]
}🟢governor_log(project_id)
Read back a project's hash-chained attempt log with chain verification.
入力スキーマ
{
"type": "object",
"properties": {
"project_id": {
"type": "string"
}
},
"required": [
"project_id"
]
}⚪governor_stats(project_id)
Concentration stats for a project (top-operator share, HHI per surface and overall).
入力スキーマ
{
"type": "object",
"properties": {
"project_id": {
"type": "string"
}
},
"required": [
"project_id"
]
}🟡verdict_submit(project_id, operator, receipt, history)
Submit a change receipt for a pre-triage verdict ($0.01/verdict x402 after the one-time 100-verdict grant; included on subscription).
入力スキーマ
{
"type": "object",
"properties": {
"project_id": {
"type": "string"
},
"operator": {
"type": "string"
},
"receipt": {
"type": "object"
},
"history": {
"type": "object"
}
},
"required": [
"project_id",
"operator",
"receipt"
]
}⚪verdict_queue(project_id)
Ranked verdict queue for a project (score desc, FIFO tie-break).
入力スキーマ
{
"type": "object",
"properties": {
"project_id": {
"type": "string"
}
},
"required": [
"project_id"
]
}⚪proxy_checkout(project_id, operator, scope)
Scoped sparse checkout through the stock-git proxy ($0.01/proxied checkout x402; requires an active Meter + Verdicts subscription). Scope paths rejecting '.', '..', absolute and '.git/' are refused.
入力スキーマ
{
"type": "object",
"properties": {
"project_id": {
"type": "string"
},
"operator": {
"type": "string"
},
"scope": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"project_id",
"operator",
"scope"
]
}⚪review_record(verdict_id, queue, reviewer_minutes, human_decision)
Record an ACTUAL human review measurement for a verdict: queue (verdict_first|fifo), reviewer_minutes spent, human_decision (land|reject). Feeds the measured reviewer-time aggregates and the false-reject sample.
入力スキーマ
{
"type": "object",
"properties": {
"verdict_id": {
"type": "string"
},
"queue": {
"type": "string"
},
"reviewer_minutes": {
"type": "number"
},
"human_decision": {
"type": "string"
}
},
"required": [
"verdict_id",
"queue",
"reviewer_minutes",
"human_decision"
]
}コミュニティ
エビデンス