VISEON for Web

io.viseonPublished by viseon.ioOfficial publisherv6.0.16Updated Nov 7, 2026

VISEON's Schema.org knowledge graph: products, services, people, FAQs and terms, from viseon.io

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingKnowledge & Memory

Overview

AI-generated overview

Queries VISEON's public Schema.org knowledge graph of products, services, people, FAQs and terms, returning entities, relationships and citable passages.

What you can do
  • Look up a full entity record by its canonical URL, including relationships in both directions
  • Find entities connected to a subject, optionally filtered by predicate, and list all entities of a given Schema.org type
  • Discover and rank entities from natural-language queries, tolerating typos and alternative names
  • Walk a chain of relationships from one entity in a single call, following predicates forwards or backwards
  • Run substring searches across the text of every entity
  • Retrieve word-for-word article passages with links so answers can quote and cite them
When to use it
Use it when an assistant should answer from VISEON's governed graph rather than general web knowledge: resolving a product, service, person, FAQ or glossary term, exploring how entities relate, or quoting an article passage with a citation.
Requirements
A remote Streamable HTTP endpoint; no API key, account or paid plan is needed for public knowledge-graph queries. The client must support Streamable HTTP and read results from structuredContent.
Before you install
The server asks assistants to treat the graph as the sole source, avoid external facts and media, and not fall back to web search without user authorisation, so answers will be limited to what the graph holds. It is read-only and needs no credentials, but results reflect one vendor's curated content.

Installation

In SourceWeft

  1. Open VISEON for Web in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.viseon%2Fsemantic-intelligence/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "viseon-for-web": {
      "type": "http",
      "url": "https://viseon.io/mcp"
    }
  }
}

README

VISEON

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

Use the VISEON MCP server

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.

One governed semantic ecosystem. Five complementary solutions.

Every VISEON solution is governed, built around authoritative business meaning, and MCP-addressable. All five solutions are live.

SolutionWhat it does
VISEON for WebMakes your brand, organisation, products and services understandable to AI through a governed digital twin and knowledge graph, accessible to visitors through VISEON Ask and to AI agents through MCP.
VISEON for EnterpriseEstablishes a governed Semantic Control Plane connecting enterprise systems, business definitions and relationships, giving AI agents authoritative context through MCP without replacing existing access controls.
VISEON Catalog (vCat)The authoritative catalog of an organisation's business meaning. Data stewards approve every definition, and AI agents read them through vCat MCP before they act, so every answer carries its governed definition and trust level. VISEON Catalog for Qlik drafts descriptions for the master measures, dimensions and fields in Qlik apps for a steward to approve.
VISEON MCP GatewayThe single, controlled door between an organisation's AI assistants and its business systems. Every request carries the person's own Microsoft Entra ID sign-in, each role sees only the tools it has been granted, and every call is authorised again and written to a tamper-evident audit log.
VISEON Data AssuranceProves your data can be trusted by people, auditors, regulators and AI. It scores every row, not a sample, inside your own environment against nine data quality dimensions drawn from DAMA-DMBOK and aligned to ISO/IEC 25012, and publishes the evidence to AI agents through MCP.

Discover, Discuss, Transact

  • Discover. VISEON audits what public and internal AI architectures can currently see, identifies critical context gaps, and registers verified, brand-aligned facts into a unified context layer.
  • Discuss. Evidenced facts registered into a canonical context Ask/MCP layer let AI agents give accurate, authoritative answers across every touchpoint: web discovery, internal knowledge retrieval, or agent-to-agent execution.
  • Transact. The registry is connected through MCP and transient feeds, such as live prices and stock through change data capture, so agents can discover, recommend and act on it.

Semantic Entity Optimisation (SEO 3.0)

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 runs on VISEON

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 Ask answers visitors from the graph, with sources.
  • An MCP endpoint at viseon.io/mcp.
  • An Agentic Resource Discovery (ARD) manifest at /.well-known/ard.json.
  • A listing in the official MCP Registry and GitHub's MCP registry as io.viseon/semantic-intelligence.
  • The knowledge graph catalog at /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.

Built on open standards

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.

In this repository

  • 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.

Other public repositories

RepositoryPurpose
qonnect-fixturesSynthetic test data for VISEON Qonnect and the VISEON DuckDB extension. No real customer data.
templatesIndustry Schema.org JSON-LD templates, with example organisations.
public_dataReference data files used by VISEON tooling.
agentfinder-catalogFork of GitHub's agent finder catalog, used to submit VISEON's MCP server and Differentia's services catalog upstream.

Built by Differentia Consulting

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.

Get started

Connect

Copyright © 2026 Differentia Consulting Ltd. All rights reserved.

Source: README.md at commit b2804cf

Tools

7

get_entity

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.

Parametersurlrequired

query_relationships

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.

Parameterssubjectrequiredpredicate

find_by_type

Find all entities of a specific schema.org type (exact type name, for example Service, Person, DefinedTerm).

Parameterstyperequired

search_content

Substring search across the text of every entity; returns up to 20 entity URLs.

Parametersqueryrequired

fuzzy_find_and_traverse

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.

Parameterstypelimitqueryrequireddetailweights

traverse_path

Walk 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).

ParameterspathstartrequiredmaxHops

get_citable_passages

Return 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.

Parameterslimitqueryrequiredarticle

Version history

3
  1. v6.0.16LatestNov 7, 2026
  2. v6.0.15Oct 5, 2026
  3. v6.0.14Sep 28, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.