trust-tools
Website security ratings, token verification, and tamper-evident ledger heads from Obelisk Gate.
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": {
"trust-tools": {
"url": "https://obeliskgate.com/mcp"
}
}
}リモートエンドポイント
https://obeliskgate.com/mcpstreamable-httpできること
ツール一覧
ツール（8）
🟢scan_trust(url)
Run Obelisk's public trust scan on an https URL — TLS and security-header posture, scored as an Obelisk Rating. Read-only, SSRF-guarded.
入力スキーマ
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The https URL to scan, e.g. https://example.com"
}
},
"required": [
"url"
]
}⚪verify_token(token)
Verify that a JSON Web Token was minted by this Obelisk Gate (ES256, correct issuer) and report its type, subject, assurance, and principal. Never returns secrets.
入力スキーマ
{
"type": "object",
"properties": {
"token": {
"type": "string",
"description": "A compact-serialized JWT issued by Obelisk (id_token or access token)."
}
},
"required": [
"token"
]
}🟢get_org_rating(org)
Read the public Obelisk Rating (0-100 score, trust band, and trend) for a registered organization by its slug.
入力スキーマ
{
"type": "object",
"properties": {
"org": {
"type": "string",
"description": "The organization slug, e.g. acme."
}
},
"required": [
"org"
]
}⚪verify_agent_run_proof(run_proof, expected_agent_id)
Verify the structural integrity, agent binding, delegation continuity, and commitments of an Obelisk action-scoped run proof. Does not reveal or infer raw task data.
入力スキーマ
{
"type": "object",
"properties": {
"run_proof": {
"type": "object",
"description": "An obelisk-agent-run-proof-v1 object."
},
"expected_agent_id": {
"type": "string",
"description": "Optional expected agt_ subject."
}
},
"required": [
"run_proof"
]
}🟢get_agent_proof(proof_id)
Read an Obelisk agent's public proof vector by opaque proof id. Returns independent claims with freshness and scope; never a scalar trust score or a claim of non-humanness.
入力スキーマ
{
"type": "object",
"properties": {
"proof_id": {
"type": "string",
"description": "The opaque id from an /agent/<proof_id> link."
}
},
"required": [
"proof_id"
]
}🟢transparency_head
Read the current signed transparency head of Obelisk's tamper-evident receipt ledger — pin it and compare later to prove history only extends. Same data as /.well-known/obelisk-transparency.json.
入力スキーマ
{
"type": "object",
"properties": {}
}🟢gate_status
Read the Gate's public liveness facts: issuer, served code revision, OIDC availability, and supported protocols. No posture internals.
入力スキーマ
{
"type": "object",
"properties": {}
}🟢explain_rating(rating, narrate)
Explain what an Obelisk Rating number means: its trust band, how the public scan scores, and what typically moves a score. Deterministic by default; pass narrate:true for an additional one-line model-written narrative (cached, public-scope, never required). Pure function of the number — no data is read.
入力スキーマ
{
"type": "object",
"properties": {
"rating": {
"type": "number",
"description": "A 0-100 Obelisk Rating, e.g. from scan_trust or get_org_rating."
},
"narrate": {
"type": "boolean",
"description": "S283 — also return `narrative`, a one-sentence model-written reading of the band (deterministic fields are always present)."
}
},
"required": [
"rating"
]
}コミュニティ
エビデンス