doom
Obsolescence-risk screening: predicts if a product gets absorbed into core LLM-platform features.
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": {
"doom": {
"url": "https://mcp.doomscore.vc"
}
}
}リモートエンドポイント
https://mcp.doomscore.vcstreamable-httpできること
ツール一覧
ツール（11）
⚪doom_prep
Prep Gate. Validates config + confirms the roadmap-signals KB is within the staleness threshold. Fails closed if stale. Call before assess_product.
入力スキーマ
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢assess_product(description, url, pitch_company_id, deck_text, mode, ...)
Assess one product's obsolescence risk. Provide exactly ONE of description/url/pitch_company_id/deck_text. Async — returns job_id; poll get_assessment. Defaults to deep mode. Optionally pass requested_by to identify the caller (shown in the activity feed).
入力スキーマ
{
"type": "object",
"properties": {
"description": {
"type": "string"
},
"url": {
"type": "string"
},
"pitch_company_id": {
"type": "string"
},
"deck_text": {
"type": "string"
},
"mode": {
"type": "string",
"enum": [
"quick",
"deep"
],
"default": "deep"
},
"requested_by": {
"type": "string",
"description": "Who is requesting this assessment (name/handle/agent id) — shown in the #doom-activity feed; defaults to anonymous."
}
},
"additionalProperties": false
}🟢get_assessment(job_id)
Poll an assessment job_id. Returns status + the typed assessment when complete. Hard timeout — never hangs on pending.
入力スキーマ
{
"type": "object",
"properties": {
"job_id": {
"type": "string"
}
},
"required": [
"job_id"
],
"additionalProperties": false
}🟢list_assessments(verdict, limit)
Recent assessments, filterable by verdict.
入力スキーマ
{
"type": "object",
"properties": {
"verdict": {
"type": "string"
},
"limit": {
"type": "number",
"default": 20
}
},
"additionalProperties": false
}⚪overview
Inspectable State. No input. Counts, recent activity, roadmap-signal freshness, health, last calibration run.
入力スキーマ
{
"type": "object",
"properties": {},
"additionalProperties": false
}⚪record_outcome(operator_key, job_id, product, actual_outcome, expected_verdict, ...)
Outcome-feedback (learning loop). Record what ACTUALLY happened to a previously-assessed product as a labeled calibration case; the weekly recalibration folds it into the gate. Operator-only (requires operator_key). Provide either job_id (links the case to that assessment + reuses its product) or product text.
入力スキーマ
{
"type": "object",
"properties": {
"operator_key": {
"type": "string"
},
"job_id": {
"type": "string"
},
"product": {
"type": "string"
},
"actual_outcome": {
"type": "string",
"enum": [
"sherlocked",
"survived",
"thrived"
]
},
"expected_verdict": {
"type": "string",
"enum": [
"roadkill",
"squeezed",
"defensible",
"riding-the-wave"
]
},
"year_observed": {
"type": "number"
},
"notes": {
"type": "string"
}
},
"required": [
"operator_key",
"actual_outcome",
"expected_verdict"
],
"additionalProperties": false
}🟢list_signal_candidates(operator_key, status, limit)
KB-refresh review queue. List auto-scraped candidate roadmap signals (default: pending). Operator-only. Approve/reject with review_signal_candidate; the weekly cron signs approved ones into the live KB.
入力スキーマ
{
"type": "object",
"properties": {
"operator_key": {
"type": "string"
},
"status": {
"type": "string",
"enum": [
"pending",
"approved",
"rejected",
"signed"
]
},
"limit": {
"type": "number",
"default": 50
}
},
"required": [
"operator_key"
],
"additionalProperties": false
}⚪review_signal_candidate(operator_key, candidate_id, action)
Approve or reject a KB-refresh candidate signal. Operator-only. Approved candidates are signed (Ed25519) into the live roadmap_signals KB by the next refresh run; rejected ones are dropped. Controls what becomes grounding truth.
入力スキーマ
{
"type": "object",
"properties": {
"operator_key": {
"type": "string"
},
"candidate_id": {
"type": "string"
},
"action": {
"type": "string",
"enum": [
"approve",
"reject"
]
}
},
"required": [
"operator_key",
"candidate_id",
"action"
],
"additionalProperties": false
}🟢list_kb_signals(operator_key)
List the active (signed, grounding) roadmap signals with their ids — use to find a signal_id to retire. Operator-only.
入力スキーマ
{
"type": "object",
"properties": {
"operator_key": {
"type": "string"
}
},
"required": [
"operator_key"
],
"additionalProperties": false
}🟢retire_signal(operator_key, signal_id, reason)
UNLEARN a KB signal that became false/obsolete (e.g. a rumored feature cancelled, or a signal no longer predictive). Soft-deletes it (active=false) so it stops grounding assessments immediately — recoverable. Operator-only. Find the id via list_kb_signals.
入力スキーマ
{
"type": "object",
"properties": {
"operator_key": {
"type": "string"
},
"signal_id": {
"type": "string"
},
"reason": {
"type": "string"
}
},
"required": [
"operator_key",
"signal_id",
"reason"
],
"additionalProperties": false
}⚪supersede_calibration_case(operator_key, case_id, reason)
UNLEARN a calibration case whose label turned out wrong or obsolete — retires it (active=false) so the recalibration gate stops scoring it. To correct, retire the wrong case then record_outcome the right one. Operator-only.
入力スキーマ
{
"type": "object",
"properties": {
"operator_key": {
"type": "string"
},
"case_id": {
"type": "string"
},
"reason": {
"type": "string"
}
},
"required": [
"operator_key",
"case_id",
"reason"
],
"additionalProperties": false
}推奨プロンプト
get_assessmentget_assessmentlist_assessmentslist_assessmentslist_assessmentsget_assessmentコミュニティ
エビデンス