io.viseon由 viseon.io 发布官方发布者v6.0.16更新于 Nov 7, 2026
VISEON's Schema.org knowledge graph: products, services, people, FAQs and terms, from viseon.io
查询 VISEON 公开的 Schema.org 知识图谱（产品、服务、人物、常见问题与术语），返回实体、关系以及可引用的段落。
Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。
把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。
阅读 https://sourceweft.com/mcp/io.viseon%2Fsemantic-intelligence/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。把它添加到你客户端的 mcpServers 配置中。
{
"mcpServers": {
"viseon-for-web": {
"type": "http",
"url": "https://viseon.io/mcp"
}
}
}Semantic Intelligence · Discover | Discuss | Transact
AI agents can't execute on canonical truth until you define it.
VISEON is a Semantic Control Plane (operating system for AI) for governing organisational meaning and evidence across enterprise systems, websites and AI interfaces. It serves as the Governed Navigator for enterprise AI, giving autonomous engines and LLMs the explicit pathways, guardrails and auditability required to discover, discuss and transact with precision.
This repository is the public reference for VISEON. The platform itself runs at VISEON.IO, which is the canonical source for what VISEON is and does. Our ARD listing for the VISEON MCP capabilities and example questions can be found here VISEON-MCP
io.viseon/semantic-intelligence — MCP developer guide covers the remote endpoint, transport, all seven tools, resources and prompt availability, authentication, VS Code / Copilot configuration and example prompts.
Connect to https://viseon.io/mcp using Streamable HTTP. Public knowledge-graph queries require no API key, account or paid plan. The ARD manifest provides complementary machine-readable discovery metadata.
Every VISEON solution is governed, built around authoritative business meaning, and MCP-addressable. All five solutions are live.
Semantic Entity Optimisation optimises the entity, not the page. Each thing an organisation is and offers gets one canonical definition, a stable identifier, verified links to the rest of the web and a record of where each fact came from, so AI reads the organisation from the source. It includes everything schema markup has always had to do, Google Rich Results included, and does not stop there.
Smarter.SEO is VISEON.IO for Qlik customers, existing and prospective, delivered by Differentia Consulting.
viseon.io is built the way VISEON builds for clients. Every page, product, service, person, glossary term and FAQ is an entity in one governed graph, served to people and to agents:
viseon.io/mcp./.well-known/ard.json.io.viseon/semantic-intelligence./wp-json/viseon/v1/catalog and a schema.txt entity index, both advertised in the HTTP Link: headers and <link rel="alternate"> elements of every page.Schema.org, JSON-LD, the Model Context Protocol, NLWeb and Agentic Resource Discovery (ARD), connected to open commerce protocols including ACP, AP2 and Google's Universal Commerce Protocol. The graph is portable, inspectable and yours.
README.md: this file.MCP-SERVER.md: the developer guide to the public VISEON MCP server.Schema.org-JSON-LD-Edge-Integrity-Test.md: a reference prompt for checking that a Schema.org @graph is fully connected by bidirectional edges.VISEON is developed by Differentia Consulting, enterprise data specialists since 2002 and a Qlik partner, who have been helping organisations prepare quality data models for business intelligence and AI. VISEON sits within the Smarter.BI solution family.
Copyright © 2026 Differentia Consulting Ltd. All rights reserved.
来源：README.md，提交 b2804cf
Get complete schema.org entity data by URL (its @id), including relationships the graph holds in either direction. Use this before selecting an entity's image or other media: retain the canonical subject ID and use only assets explicitly linked by the retrieved record. A matching name, caption or filename alone does not establish identity. If no supported asset is available, state the limitation; do not add externally searched media to a KG-grounded answer.
url必填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.
subject必填predicateFind all entities of a specific schema.org type (exact type name, for example Service, Person, DefinedTerm).
type必填Substring search across the text of every entity; returns up to 20 entity URLs.
query必填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. The optional detail argument is summary (for each hit: id, type, name, url, the start of the description and the match score) or full (every property and relationship). A client on protocol 2026-07-28 or later gets summary unless it asks for full; an older client gets full unless it asks for summary.
typelimitquery必填detailweightsWalk the knowledge graph from one entity in a single call. start: an entity @id or a name (resolved like fuzzy_find_and_traverse). path: one entry per hop, each a predicate or a list of predicates; prefix a predicate with ^ to follow it backwards (e.g. ^worksFor finds who works for an organisation). Literal values (dates, names, emails) named in a hop are returned in values. Example, who founded the company Hamza works for and when: start "Hamza Ashraf", path [["worksFor"], ["founder", "foundingDate"]]. Without path, follows every link for maxHops (1-3, default 2) and returns links only, with a budget of 100 rows shared between hops, so hubs are cut short rather than hiding later hops (use a path to go deeper: a path call may return up to 400 rows). Returns edges [{hop, from, predicate, to, to_name, to_types}], values [{hop, subject, subject_name, predicate, value}], truncated and truncated_hops (the hops that hit a limit).
pathstart必填maxHopsReturn passages of the VISEON articles word for word, each with a link to the passage itself, the article it is part of and how much of the query it holds, so an answer can quote and cite them. query: the distinctive words asked about (a name, a term, a phrase the article uses). article: optional, an article's @id, page url or title, to look inside that article only. limit: 1 to 5 passages, default 3. The text is verbatim and unaltered: no model has read or paraphrased it. It matches the article's own words, so ask in the words the article would use; for what the graph says about an article (description, author, date, topics) use fuzzy_find_and_traverse and get_entity.
limitquery必填article已满足适用检查项的 90%
该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。
请在仓库或注册中心条目中声明许可证。