ruthven
Read-only artwork provenance: Origin Passports, evidence states, Merkle proofs checkable on Ethereum
我该使用它吗
质量与安全性
发现(3)
- HIGH
- MEDIUM在 ruthven_describe 中
- INFO在 ruthven_describe 中
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": {
"ruthven": {
"url": "https://ruthven.ai/api/ruthven/mcp"
}
}
}远程端点
https://ruthven.ai/api/ruthven/mcpstreamable-http它能做什么
工具清单
工具(8)
🟢ruthven_get_asset(asset_id, include_evidence)
The universal RUTHVEN asset record: identity, tokenization, provenance, source works, components, construction sequence, hashes, documents, rights, verified / contextual / inferred facts, unknowns, and counts. Claims carry evidence ids; pass include_evidence=true for the full evidence records as well (large).
输入模式
{
"type": "object",
"properties": {
"asset_id": {
"type": "string",
"description": "The asset: \"PT-0001\", a RUTHVEN ID such as \"RUTHVEN-PT-0000001\", or a work number such as \"1\"."
},
"include_evidence": {
"type": "boolean",
"description": "Include every evidence record and the evidence graph. Default false."
}
},
"required": [
"asset_id"
],
"additionalProperties": false
}🟢ruthven_list_evidence(asset_id, status, type, kind, q, ...)
The evidence records behind an asset, each with a stable evidence_id, its source (document, locator, ipfs uri, gateway url, ledger claim id), a SHA-256, a verification state and freshness timestamps. Filter by status (VERIFIED, CONTEXT, INFERRED), type, kind, or a text query.
输入模式
{
"type": "object",
"properties": {
"asset_id": {
"type": "string",
"description": "The asset: \"PT-0001\", a RUTHVEN ID such as \"RUTHVEN-PT-0000001\", or a work number such as \"1\"."
},
"status": {
"type": "string",
"enum": [
"VERIFIED",
"CONTEXT",
"INFERRED"
]
},
"type": {
"type": "string"
},
"kind": {
"type": "string"
},
"q": {
"type": "string",
"description": "Text to look for in the label or statement."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 500
},
"offset": {
"type": "integer",
"minimum": 0
}
},
"required": [
"asset_id"
],
"additionalProperties": false
}🟢ruthven_get_evidence(asset_id, evidence_id)
Retrieve the source record behind a stable evidence id (EVID-…) or an unknown id (UNK-…): where it was read from, its hash, its state, and how fresh it is.
输入模式
{
"type": "object",
"properties": {
"asset_id": {
"type": "string",
"description": "The asset: \"PT-0001\", a RUTHVEN ID such as \"RUTHVEN-PT-0000001\", or a work number such as \"1\"."
},
"evidence_id": {
"type": "string"
}
},
"required": [
"asset_id",
"evidence_id"
],
"additionalProperties": false
}🟢ruthven_get_provenance(asset_id)
Provenance and lineage: the timeline, source works, generated elements, components, the construction sequence, relationships, chain identity, tokenization, and the evidence graph (cut_from, placed_as, pinned_as, pictured_by, hash_of).
输入模式
{
"type": "object",
"properties": {
"asset_id": {
"type": "string",
"description": "The asset: \"PT-0001\", a RUTHVEN ID such as \"RUTHVEN-PT-0000001\", or a work number such as \"1\"."
}
},
"required": [
"asset_id"
],
"additionalProperties": false
}🟢ruthven_verify_claim(asset_id, evidence_ids)
Given the evidence ids a claim rests on, return the state the claim earns (the weakest among them), each record's hash and location, and how to check it independently of RUTHVEN. Deterministic; no model is involved.
输入模式
{
"type": "object",
"properties": {
"asset_id": {
"type": "string",
"description": "The asset: \"PT-0001\", a RUTHVEN ID such as \"RUTHVEN-PT-0000001\", or a work number such as \"1\"."
},
"evidence_ids": {
"type": "array",
"items": {
"type": "string"
},
"minItems": 1,
"maxItems": 50
}
},
"required": [
"asset_id",
"evidence_ids"
],
"additionalProperties": false
}🟢ruthven_get_proof(asset_id, evidence_ids, paths)
A Merkle proof that evidence records are part of the issued Origin Passport, with the entry each rests on and the steps to check it without trusting RUTHVEN: SHA-256 over the entry, keccak256 up the proof, and the root compared with the one in the published Passport. It proves that the record contains the entry; it does not make a statement true. With neither evidence_ids nor paths, returns the paths that can be proved. Deterministic; no model is involved.
输入模式
{
"type": "object",
"properties": {
"asset_id": {
"type": "string",
"description": "The asset: \"PT-0001\", a RUTHVEN ID such as \"RUTHVEN-PT-0000001\", or a work number such as \"1\"."
},
"evidence_ids": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 50,
"description": "Stable evidence ids (EVID-…)."
},
"paths": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 50,
"description": "Entry paths in the Passport, e.g. \"identity.name\" or \"module.collection.copyrightOwner\"."
}
},
"required": [
"asset_id"
],
"additionalProperties": false
}🟢ruthven_ask(asset_id, question)
Ask a question about one asset. Returns structured JSON only: an answer, claims (each with a verification state and the evidence ids it rests on), unknowns, the full cited evidence records, and follow-up questions. Never a valuation; never a recommendation to act.
输入模式
{
"type": "object",
"properties": {
"asset_id": {
"type": "string",
"description": "The asset: \"PT-0001\", a RUTHVEN ID such as \"RUTHVEN-PT-0000001\", or a work number such as \"1\"."
},
"question": {
"type": "string",
"maxLength": 500
}
},
"required": [
"asset_id",
"question"
],
"additionalProperties": false
}🟢ruthven_describe
What RUTHVEN is and what an agent may do with it: the verification states, the permission model (READ and ANALYSE only), the asset types (live and placeholder), and the JSON API endpoints.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": false
}社区
证据