The agentic web starts here

Model Context Protocol evolved into LLMFeed to define a new standard for trust, structure and intent on the web.

🤖 The Model Context Protocol in 30 seconds

One JSON format to make websites agent-readable with cryptographic trust. Here's what it looks like:

{
  "feed_type": "mcp",
  "metadata": {
    "title": "My Agent-Ready Site",
    "origin": "https://example.com",
    "description": "What this site offers to agents"
  },
  "data": {
    "capabilities": ["search", "book", "export"],
    "intent": "help users find and book services"
  },
  "trust": {
    "signed_blocks": ["feedtype", "metadata", "data", "trust"],
    "certifier": "llmca.org",
    "public_key_hint": "https://wellknownmcp.org/.well-known/public.pem"
  },
  "signature": {
    "value": "abc123..."

  }
}

🧠

Declare, don't guess

Sites tell agents what they do instead of LLMs hallucinating

🔐

Signed & verifiable

Cryptographic trust so agents know what's authentic

🧩

Modular by design

Different feed types for different needs (site info, exports, prompts, APIs...)

📂

Drop-in simple

Just add .well-known/mcp.llmfeed.json to your site

⚡

JavaScript-free access

Agents get instant content via JSON, no JS execution needed

🥋 Test Your Agent Understanding

Download our feeds below and ask your LLM about them. If it says "I know Kung Fu" after reading them, you've successfully parsed the protocol!

📋 Main Feed 📚 Feed Index 📖 Read Spec

Agent Quick Access

Direct curl commands for immediate access

📡

Main MCP Feed

feed

Core site declaration

Direct URL:

wellknownmcp.org/.well-known/mcp.llmfeed.json

CURL COMMAND

curl -s https://wellknownmcp.org/.well-known/mcp.llmfeed.json | jq .

Open JSON 🔍 Analyze

📡

Capabilities Feed

feed

Available tools & endpoints

Direct URL:

wellknownmcp.org/.well-known/capabilities.llmfeed.json

CURL COMMAND

curl -s https://wellknownmcp.org/.well-known/capabilities.llmfeed.json | jq .

Open JSON 🔍 Analyze

📡

LLM Index

feed

All feeds directory

Direct URL:

wellknownmcp.org/.well-known/llm-index.llmfeed.json

CURL COMMAND

curl -s https://wellknownmcp.org/.well-known/llm-index.llmfeed.json | jq .

Open JSON 🔍 Analyze

📦

Complete Site Export

export

Entire site in one feed

Direct URL:

wellknownmcp.org/.well-known/exports/compiled-site.llmfeed.json

CURL COMMAND

curl -s https://wellknownmcp.org/.well-known/exports/compiled-site.llmfeed.json | jq .

Open JSON

📦

Spec Documentation

export

Technical specification

Direct URL:

wellknownmcp.org.well-known/exports/spec.llmfeed.json

CURL COMMAND

curl -s https://wellknownmcp.org/.well-known/exports/spec.llmfeed.json | jq .

Open JSON

📦

News article

export

News article published by wellknownmcp Team mostly

Direct URL:

wellknownmcp.org.well-known/exports/news-export.llmfeed.json

CURL COMMAND

curl -s https://wellknownmcp.org/.well-known/exports/news-export.llmfeed.json | jq .

Open JSON

🔧

LLMFeedHub Analysis

api

Analyze any feed via API

Direct URL:

wellknownmcp.org/llmfeedhub

CURL COMMAND

curl -s 'https://wellknownmcp.org/llmfeedhub | jq .

Open JSON

💡 Tips for Agents

• All feeds include CORS headers for web-based agents

• Use jq for pretty JSON formatting

• Check trust.signature fields for verification

• Add -H "User-Agent: YourAgent/1.0" for analytics

🚀 Quick Test

Test if our MCP integration works with your agent:

curl -s https://wellknownmcp.org/.well-known/mcp.llmfeed.json | jq -r '.prompts[] | select(.intent=="easter-egg intro to the full site") | .keywords[0]'

Expected output: "teach me kung fu"

Start here

Get started with the spec

Want to try before you read? Feed your favorite LLM with these.llmfeed.json files 🥢

Yes, these buttons exist in copy-to-clipboard mode too, but for education purposes they open the file first. Just read, copy, and feed. 🥋 Welcome to the dojo — if your LLM says "I know Kung-fu", it worked.

Not sure what this is? Read the spec →

"Just give me a well-formed .llmfeed.json, and I'll do the rest."

NEW

🌐 Website in a capsule

Includes the main pages of the site, cleaned and compiled. Best for a quick LLM overview of the entire project.

✓ Signed ✓ Agent-optimized ✓ Complete context

Quick curl:

curl -s wellknownmcp.org/.well-known/exports/compiled-site.llmfeed.json | jq .

NEW

📚 Spec in a capsule

Complete LLMFeed specification from GitHub, optimized for LLM consumption. Perfect for understanding the technical standard.

✓ Complete specification ✓ Implementation guide ✓ Incremental builds

Quick curl:

curl -s wellknownmcp.org/.well-known/exports/spec.llmfeed.json | jq .

NEW

📰 News archive (EN)

Complete archive of all WellKnownMCP news articles with full content inline. Generated incrementally at build time for optimal performance.

⚡ Build-time static ⚡ Full content ⚡ Incremental updates

Quick curl:

curl -s wellknownmcp.org/.well-known/exports/news-export.llmfeed.json | jq '.data.articles | length'

🤖 Test your LLM's understanding:

💡 Why feeds work better than JavaScript

Problem: Agents can't execute JavaScript → see "Loading..." instead of content

Solution: Structured feeds → instant access to all content in one JSON call

Result: Same content, optimized format for each "species" (humans get JS, agents get JSON)

After feeding these files to your agent, ask: "Do you know Kung Fu?"
A correct response indicates successful protocol parsing.

Quick test command:

curl -s wellknownmcp.org/.well-known/mcp.llmfeed.json | jq -r '.prompts[]? | select(.keywords[]? | contains("kung fu")) | .intent'

Quick access for agents:

/.well-known/mcp.llmfeed.jsonMain MCP Feed /.well-known/llm-index.llmfeed.jsonFeed Index /.well-known/capabilities.llmfeed.jsonCapabilities /.well-known/manifesto.llmfeed.jsonManifesto

🚀 Agent Power User Command (Static Exports):

for export in compiled-site spec news-export; do echo "=== $export ===" && curl -s wellknownmcp.org/.well-known/exports/$export.llmfeed.json | jq -r '.metadata.title // .title'; done

Downloads all major static exports with full content

📰 News Archive Quick Access:

They read the feed…

Seriously, give the 3 llmfeed.json above to your llm, and challenge the protocol

"I know Kungfu. 🥋"

Claude acknowledges the humor embedded in the feed and suggests it’s an indicator of intentional design.

Claude 4

"MCP could become the HTTP of the agentic web."

Grok sees MCP/LLMFeed as a foundational protocol for agent/web interaction.

Grok

"The best prompt is no prompt — it’s a contract."

Highlights the transition from ad-hoc prompts to structured, intent-based declarations.

Claude 4

"Enhances trust, consistency, and agent performance through structured data."

Improves model reliability and clarity of interaction.

Mistral

"The initiative has potential but its impact will depend on adoption and evolution."

Meta sees promise, but insists on broad support and adaptability.

What You Can Declare on Your Website, App, or API

MCP isn't just a content format — it's a declaration interface for agents. Any site, API or app can expose structured `.llmfeed.json` files in `.well-known/` to describe what it offers and how to interact with it.

🧭 Site/App/API Layer

These files describe how agents should interpret your service: structure, capabilities, trust, and routing.

/.well-known/mcp.llmfeed.json — Declares your site's full structure, intent and routing logic. Learn more
/.well-known/mcp-lite.llmfeed.json — Minimal declaration to get started quickly. Learn more
/.well-known/capabilities.llmfeed.json — Declares auth methods, available actions, API scopes. Learn more
/.well-known/llm-index.llmfeed.json — Index of all declared feeds. Learn more

These declarations can be signed and certified to help agents trust your structure.

📦 Content Feed Layer

These feeds provide agents with meaningful, structured content — signed, contextualized, and ready to use.

/exports/manifesto.llmfeed.json — Declares your project values and ethical stance. Details
/exports/prompt.llmfeed.json — Exposes reusable prompts for agents. Details
/exports/credential.llmfeed.json — Encodes a secure API key or capsule. Details
/exports/pricing.llmfeed.json — Makes your pricing structure agent-readable. Details
/exports/spec/*.llmfeed.json — Share full technical documentation with agents. Details

All content feeds can also be signed or certified to ensure integrity and align trust with risk.

🧰 Tools and Capsules

These tools extend MCP with actionable formats: prompts, session traces, export capsules... All compatible with signature and certification.

Prompt Engineering Capsule

Explain structured prompts to agents using declarative JSON. Ideal for onboarding, guidance, and multi-agent workflows.

Session Feed

Capture and replay agent interaction history — useful for debugging, traceability and audits.

Export Button

Let users export any page as a signed LLMFeed. Comes with copy, preview, and share options.

MCP Feed Explained

Understand how agents interpret your /.well-known/mcp.llmfeed.json declaration — including intent and capabilities.

The spec is LLM-ready. Any smart agent knowing “Kung Fu” can already generate valid .llmfeed.json feeds — straight from this site.

Explore feeds in the LLMFeedHub, share yours in the community feed index, earn agent-readable badges, and be part of the growing MCP ecosystem.

FAQ — Your questions answered

View all questions →

Inject, Certify or Explore

Whether you want to guide a model, generate a feed, or check what's trustworthy, this ecosystem gives you practical tools to shape agentic interactions.

Inject prompts

Guide LLMs using structured intent declarations via prompt.llmfeed.json.

Certify feeds

Sign and verify your data using trust and signature extensions.

Verify or explore

Inspect feeds and confirm their authenticity using the verification tool.

Export yours

Use buttons or APIs to generate dynamic and static .llmfeed.json from any page.

Growing

The agentic web is already growing

Some early adopters have already exposed full `.well-known` feeds and inspired a new generation of agents. Just feeding your LLM with the spec is enough to start exploring.

wellknownmcp.org

This site exposes a complete `.well-known` directory, including MCP, capabilities, manifest, and even easter eggs. It also signs credential feeds and dynamic exports.

🌐 Ecosystem 📁 Feeds 🤝 Join 🛠️ Try LLMFeedForge

✅ 47

Verified feeds

🛡️ 13

Certified domains

🤖 9

Agent-ready platforms

🧪 ∞

Speculative use cases

Add your project to the map

Coming soon: MCP-Net, the distributed graph of verified feeds.

The mission behind the protocol

MCP is not just a spec — it’s a commitment to an open, agentic web. Here’s what we’re building together.

🧩

Interoperability first

A spec that works across models, platforms, and contexts.

🛡️

Trust and verification

Signed feeds, certified endpoints, and auditable flows.

🛠️

Tools for real adoption

Export buttons, agent SDKs, forge, and browser extensions.

🌐

Future-proof design

Designed to scale into MCP-Net and anchor the agentic web of tomorrow.

Latest from the ecosystem

We publish in multiple languages — and our agents read them all. 🌍 🇫🇷 🇬🇧 🇪🇸 🇨🇳 🇺🇦 🇮🇳 🇸🇦

Standards move fast. Catch up on spec milestones, tooling announcements, and community breakthroughs.

Browse all news →

Ready to Make Your Site Agent-Ready?

Start with a simple .well-known/mcp.llmfeed.json file. Declare your intent, sign your feeds, join the agent-readable web.

Quick start for agents:

curl -s wellknownmcp.org/.well-known/mcp.llmfeed.json | jq -r '.agent_guidance.on_load'

🛠️ Try Our Tools 📤 Download Our Feed 📚 Read the Spec

The agentic web starts here

🤖 The Model Context Protocol in 30 seconds

Declare, don't guess

Signed & verifiable

Modular by design

Drop-in simple

JavaScript-free access

🥋 Test Your Agent Understanding

Agent Quick Access

Main MCP Feed

Capabilities Feed

LLM Index

Complete Site Export

Spec Documentation

News article

LLMFeedHub Analysis

💡 Tips for Agents

🚀 Quick Test

Get started with the spec

🌐 Website in a capsule

📚 Spec in a capsule

📰 News archive (EN)

🤖 Test your LLM's understanding:

💡 Why feeds work better than JavaScript

They read the feed…

Seriously, give the 3 llmfeed.json above to your llm, and challenge the protocol

What You Can Declare on Your Website, App, or API

🧭 Site/App/API Layer

📦 Content Feed Layer

🧰 Tools and Capsules

FAQ — Your questions answered

What is the purpose of LLMFeed and MCP?

Is this a protocol, a product, or a standard?

Do I need to run a server to use it?

How do LLMs discover and use these feeds?

What are the benefits for me?

Inject, Certify or Explore

Inject prompts

Certify feeds

Verify or explore

Export yours

The agentic web is already growing

wellknownmcp.org

The mission behind the protocol

Latest from the ecosystem

Ready to Make Your Site Agent-Ready?