The Knowledge MCP is an open endpoint through which we serve our complete documentation and platform knowledge: how things are addressed in Laioutr and how they have to work. Whether it's Claude, Gemini, GPT, your own model or a developer – over MCP everyone retrieves the knowledge to build frontend components, apps and integrations correctly against the platform.
KNOWLEDGE MCP FOR DOCUMENTATION
Our platform knowledge, retrievable by any AI system.
Over an open MCP endpoint, Laioutr serves its complete documentation and platform knowledge – machine-readable, schema-aware and retrievable by any AI system.
An open knowledge endpoint by Laioutr · Berlin · since 2024
Models can build – with the right knowledge
Claude, Gemini, GPT and the like can understand structure and generate code today. But the result is only good with current, structured knowledge about the platform. So the question is not whether a model can build, but whether it has the knowledge it needs at hand.
MCP is the open standard for it
Instead of maintaining a separate knowledge source for every model, MCP provides a common language through which every compatible client retrieves the same documentation. Laioutr relies on exactly that, rather than on a closed proprietary solution.
Building needs the knowledge at hand
Components, apps and integrations are built continuously, not just once at launch. Building correctly against Laioutr means having the knowledge on hand at all times – schemas, field types and conventions, instead of digging through scattered doc pages.
The definition
What is the Knowledge MCP?
The Knowledge MCP (at its core the MCP for our documentation) is an open endpoint through which we serve all of our knowledge about how things are addressed in the Laioutr platform and how they have to work. An agent or developer – whether built on Claude, Gemini, GPT, or a custom model – retrieves guides, component and section schemas, field types, conventions, and examples through it, in machine-readable form.
The Knowledge MCP changes nothing on your frontend. It delivers the knowledge you need to build frontend components, apps, and integrations – regardless of which vendor is behind the model.
MCP endpoint - the open access point
Every Laioutr project exposes an MCP endpoint that follows the open Anthropic standard. Any MCP-capable client can connect and retrieve the documentation, no proprietary SDK required.
What it enables:
Direct, standardized access to docs, schemas, and examples, without a custom integration per model vendor.
Schema context - the platform docs are machine-readable
An agent doesn't just get the docs, it gets context. Component schemas, slot rules, and field types are available in machine-readable form before anything is built.
What it enables:
The agent understands which fields a section has and which blocks belong in which slot, instead of guessing.
Retrieval - docs, schemas, field types, examples
The MCP provides concrete tools: search the docs, retrieve component and section schemas, look up field types, fetch examples, check conventions. Everything you need to build correctly against the platform is available in machine-readable form.
What it enables:
From a quick lookup to a pipeline that retrieves the knowledge for ten integrations in one run.
Model-agnostic connection - your choice
Because MCP is an open standard, it doesn't matter whether Claude from Anthropic, Gemini from Google, a GPT model, or your own inference runs behind it. Every agent retrieves the same knowledge in the same language.
What it enables:
No lock-in to one model vendor, you switch or combine models without rebuilding access to the knowledge.
Governance - permissions instead of a black box
Every MCP access runs through clearly assigned permissions. You define which projects and which parts of the documentation an agent is even allowed to see, with guardrails against unwanted access.
What it enables:
Serving knowledge without losing control, every retrieval stays traceable and within a predefined scope.
Every generation solved a real problem and created a new one. The MCP generation solves the knowledge problem: that platform knowledge used to live only in doc pages made for humans, not machine-readable for agents. Now the same knowledge is available to any AI system and any developer, on demand.
IDEAS & EXAMPLES
What you can build with the Knowledge MCP
The examples below are ideas, not a fixed feature list. What you build with the Knowledge MCP depends on your use case, your team, and your stack.
What they share: the MCP delivers the knowledge to build correctly against Laioutr. You decide which models and which tools consume that knowledge.
Build frontend components
Over the MCP, an agent or developer retrieves the component schemas, field types, and conventions and builds frontend components correctly against Laioutr – schema-compliant instead of guessed.
Create sections & blocks
The MCP delivers slot rules, restrictTo/allow, and field types, so sections and blocks are created schema-compliant from the start – without digging through scattered docs.
Scaffold apps
With the platform knowledge at hand, a Laioutr app can be scaffolded from scratch: structure, entrypoints, and conventions come straight from the docs, not from guesswork.
Connect integrations
When connecting a backend, a PIM, or a third-party service, you retrieve the right interfaces, data types, and examples over the MCP – and build the integration against the documented state, not against assumptions.
Look up schemas & conventions
Look up at any time which fields a section has, which field type is expected, and which convention applies – retrievable in machine-readable form, instead of clicking through doc pages.
Validate implementation
An agent can validate an implementation against the documented state – missing fields, wrong field types, or violated slot rules – and present the findings in an understandable way.
Architecture
How this fits together technically
For the tech leads in the room: here's the architecture, without the marketing filter.
An external model or developer (Claude, Gemini, GPT, or your own) queries the Laioutr documentation over MCP. The platform keeps guides, schemas, and field types indexed and machine-readable, and returns exactly the slice of knowledge the client requests for its build.
Clear boundaries
What the Knowledge MCP is not
So there's no confusion, three clarifications on categories the Knowledge MCP tends to get mixed up with.
Compare differences | Nicht das | Sondern das |
|---|---|---|
Was die MCP-Schnittstelle nicht ist Damit es keine Verwechslung gibt — drei Klarstellungen zu Kategorien, mit denen eine offene MCP-Schnittstelle gerne verwechselt wird. | ||
Modell-Lock-in Wo geschlossene Integrationen aufhören und eine offene Schnittstelle anfängt. | Eine proprietäre Integration, die dich an einen einzigen Modell-Anbieter bindet. Geschlossene Anbindungen erzeugen Lock-in — MCP erzeugt Wahlfreiheit. | Eine offene, modell-agnostische Schnittstelle nach dem Anthropic-Standard — Claude, Gemini, GPT oder ein eigenes Modell, deine Wahl. |
Chatbot-Widget Der Unterschied zwischen einem aufgesetzten Assistenten und echter Administration. | Ein aufgesetztes Chatbot-Widget, das nur Fragen beantwortet, aber nichts am Frontend selbst ändert. Chatbots reden über die Seite — MCP steuert sie. | Ein Administrations-Layer, über den Agenten Seiten, Sections und Inhalte strukturell lesen und verändern können. |
Blackbox-Automatisierung Warum Kontrolle kein Widerspruch zu Automatisierung ist. | Eine Blackbox, die unkontrolliert am Frontend schraubt. Ohne Schema-Kenntnis und Freigaben wäre Automatisierung ein Risiko — mit MCP ist sie es nicht. | Schema-aware und rechte-basiert: jede Aktion läuft innerhalb klar definierter Guardrails und bleibt nachvollziehbar. |
FOR WHOM
Who is the Knowledge MCP made for?
Developers & teams building on Laioutr
A fit if:
You build frontend components, sections, or blocks for Laioutr and need to stay schema-compliant.
You'd rather have schemas and conventions on demand than dig through scattered doc pages.
You use agents or scripts that need the platform knowledge at build time.
App & integration providers
A fit if:
You develop apps or integrations for the Laioutr platform and want to build against the documented state.
You want to retrieve interfaces, data types, and examples in machine-readable form instead of guessing.
You want to validate your integration against the docs before it goes live.
Agencies & solution partners
A fit if:
You build frontends for several clients and want to set up your own build and automation pipelines.
You want your tools and agents to retrieve the Laioutr knowledge directly, instead of maintaining it by hand.
You value an open interface over proprietary point solutions.
Developers & teams building on Laioutr
A fit if:
You build frontend components, sections, or blocks for Laioutr and need to stay schema-compliant.
You'd rather have schemas and conventions on demand than dig through scattered doc pages.
You use agents or scripts that need the platform knowledge at build time.
App & integration providers
A fit if:
You develop apps or integrations for the Laioutr platform and want to build against the documented state.
You want to retrieve interfaces, data types, and examples in machine-readable form instead of guessing.
You want to validate your integration against the docs before it goes live.
Agencies & solution partners
A fit if:
You build frontends for several clients and want to set up your own build and automation pipelines.
You want your tools and agents to retrieve the Laioutr knowledge directly, instead of maintaining it by hand.
You value an open interface over proprietary point solutions.
Security through permissions
Approvals and guardrails instead of uncontrolled access
You define the scope
Model freedom
Claude, Gemini, GPT, or your own model
No vendor lock-in
Scalability
From a single lookup to large-scale retrieval
Via API, script, or agent
Open standard
Anthropic specification, schema-aware instead of a black box
Every retrieval follows the open standard
Officially listed
Verified listing, connect directly from Claude
In the Anthropic connector store
MORE INTEGRATIONS
MCP is one channel among several
Beyond the open MCP standard, the platform knowledge is also reachable directly from other agent interfaces – two current examples:
ChatGPT Plugin
Retrieves the Laioutr platform knowledge directly from ChatGPT – docs, schemas, and examples for your build.
FAQ
The interface is new, and with it come questions — we answer the most important ones here
Any MCP-capable client, whether Claude from Anthropic, Gemini from Google, a GPT model, or your own inference. MCP is an open standard, not an Anthropic-exclusive feature. You're not tied to one vendor.
Every MCP access runs through clearly assigned permissions. You define which projects and which parts of the documentation an agent may retrieve. Guardrails prevent unwanted access, and every retrieval stays traceable and within a predefined scope.
The entire platform knowledge: guides, component and section schemas, field types, slot rules, conventions, and examples. All of it retrievable in machine-readable form, everything you need to build frontend components, apps, and integrations correctly against Laioutr.
No. MCP is an open standard, not a protocol tied to Laioutr or a single vendor. You can connect Claude, Gemini, GPT, an open-source model, or your own inference, and switch at any time without rebuilding access to the knowledge.
No. The Knowledge MCP is read-only: it serves documentation, schemas, and examples, but changes nothing on your frontend. Building and deciding stay with you, the MCP only delivers the knowledge for it.
Not necessarily for the standard case, an MCP-capable client connects directly to the endpoint. For custom pipelines, scripts, or deeper automation, technical support helps. We guide you through the setup, you don't start alone.
That depends on the platform tier and scope of use. You'll find a transparent overview on our Pricing page. In a conversation, we'll look together at what your specific build use case looks like.
BUILD CONVERSATION
Ready to build with our platform knowledge?
Let's talk about what you're building. We'll show you which platform knowledge the Knowledge MCP already delivers today, and what of it moves your team forward.
"After 30 minutes, we knew Laioutr makes our replatforming feasible." - Daniel B., CEO, hygibox.de