trust-tools
Website security ratings, token verification, and tamper-evident ledger heads from Obelisk Gate.
我该使用它吗
质量与安全性
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"trust-tools": {
"url": "https://obeliskgate.com/mcp"
}
}
}远程端点
https://obeliskgate.com/mcpstreamable-http它能做什么
工具清单
工具（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.
输入模式
{
"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.
输入模式
{
"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.
输入模式
{
"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.
输入模式
{
"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.
输入模式
{
"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.
输入模式
{
"type": "object",
"properties": {}
}🟢gate_status
Read the Gate's public liveness facts: issuer, served code revision, OIDC availability, and supported protocols. No posture internals.
输入模式
{
"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.
输入模式
{
"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"
]
}社区
证据