NLWeb simplifies the process of building conversational interfaces for websites. It natively supports MCP (Model Context Protocol), allowing the same natural language APIs to serve both humans and AI agents.
Schema.org and related semi-structured formats like RSS — used by over 100 million websites — have become not just de facto syndication mechanisms, but also a semantic layer for the web. NLWeb leverages these to enable natural language interfaces more easily.
What is NLWeb?
NLWeb is a collection of open protocols and associated open source tools. Its main focus is establishing a foundational layer for the AI Web — much like HTML revolutionized document sharing.
To make this vision reality, NLWeb provides practical implementation code — not as the definitive solution, but as proof-of-concept demonstrations showing one possible approach. We expect and encourage the community to develop diverse, innovative implementations that surpass these examples.
This mirrors the web's own evolution, from the humble htdocs folder in NCSA's HTTP server to today's massive data center infrastructures — all unified by shared protocols that enable seamless communication.
AI has the potential to enhance every web interaction. Realizing this requires a collaborative spirit reminiscent of the Web's early "barn raising" days. Shared protocols, sample implementations, and community participation are all essential.
NLWeb brings together protocols, Schema.org formats, and sample code to help sites quickly implement conversational endpoints — benefitting both users through natural interfaces and agents through structured interaction.
How It Works
NLWeb has two primary components:
Natural Language Protocol
A simple protocol to interact with a site using natural language. It returns responses in JSON using Schema.org vocabulary.
Structured Implementation
Uses existing markup on sites with structured lists (products, recipes, reviews). Combined with UI widgets, conversational interfaces can be added with ease.
NLWeb and MCP/A2A
MCP and A2A are emerging standards for enabling chatbots and AI assistants to interact with tools and each other. Every NLWeb instance also acts as an MCP server (and soon A2A) and supports a core method, ask, which allows a natural language question to be posed to a website.
The response returned uses Schema.org — a widely adopted vocabulary for describing web data.
NLWeb is to MCP/A2A what HTML is to HTTP.
Where We're Building
We've been following NLWeb closely — we like the direction a lot. Treating "talking to a site" as a standard, and defining consistent endpoints for agents to consume, feels like the right foundation.
Where we think we can contribute is the next layer: extending NLWeb so that "talking to a company" isn't only free-form Q&A — it also supports structured discovery and actions that reflect how B2B companies actually operate.
Concretely, we're exploring an extension model that adds:
- Capability Discovery A standardized way for a company endpoint to advertise what it can do (beyond chat)
- B2B Qualification Loops The endpoint can ask follow-up questions — security requirements, deployment constraints, timeline, budget bands, integrations — before producing a final answer or enabling actions
- Action Endpoints Schedule a technical deep-dive, request a quote, start a trial, open a support ticket, route to the right product line/region, fetch security docs (SOC2/ISO)
- Verified Responses Authoritative answers with structured fields (not just prose), designed to reduce hallucination and stale web scraping
Join the Agentic Web
Explore our specification and see how we're building on these open standards.