VISEON Ask
VISEON's Schema.org knowledge graph: products, services, people, FAQs and terms, from viseon.io
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": {
"semantic-intelligence": {
"url": "https://viseon.io/mcp"
}
}
}远程端点
https://viseon.io/mcpstreamable-http它能做什么
工具清单
工具（5）
🟢get_entity(url)
Get complete schema.org entity data by URL (its @id), including relationships the graph holds in either direction.
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string"
}
},
"required": [
"url"
]
}输出模式
{
"type": "object",
"additionalProperties": true
}🟢query_relationships(subject, predicate)
Find entities connected to a subject: one row per property value, with object_type 'uri' for links to other entities and 'literal' for values. Optionally filter by predicate.
输入模式
{
"type": "object",
"properties": {
"subject": {
"type": "string"
},
"predicate": {
"type": "string"
}
},
"required": [
"subject"
]
}输出模式
{
"type": "object",
"properties": {
"items": {
"type": "array",
"items": {
"type": "object"
}
},
"count": {
"type": "integer"
}
},
"required": [
"items",
"count"
]
}🟢find_by_type(type)
Find all entities of a specific schema.org type (exact type name, for example Service, Person, DefinedTerm).
输入模式
{
"type": "object",
"properties": {
"type": {
"type": "string"
}
},
"required": [
"type"
]
}输出模式
{
"type": "object",
"properties": {
"items": {
"type": "array",
"items": {
"type": "string"
}
},
"count": {
"type": "integer"
}
},
"required": [
"items",
"count"
]
}🟢search_content(query)
Substring search across the text of every entity; returns up to 20 entity URLs.
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string"
}
},
"required": [
"query"
]
}输出模式
{
"type": "object",
"properties": {
"items": {
"type": "array",
"items": {
"type": "string"
}
},
"count": {
"type": "integer"
}
},
"required": [
"items",
"count"
]
}🟢fuzzy_find_and_traverse(query, type, limit, weights)
Find and rank schema.org entities from natural language, tolerating typos and alternative names. Returns bounded entity context with relationship IDs; use get_entity for full detail.
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string"
},
"type": {
"type": "string"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 10,
"default": 5
},
"weights": {
"type": "object",
"properties": {
"predicates": {
"type": "object"
},
"entityTypes": {
"type": "object"
}
}
}
},
"required": [
"query"
]
}输出模式
{
"type": "object",
"properties": {
"items": {
"type": "array",
"items": {
"type": "object"
}
},
"count": {
"type": "integer"
}
},
"required": [
"items",
"count"
]
}社区
证据