Public knowledge interface

Let Agents use this site

Every interface exposes only public, read-only documents. Search, reading, and relationships share the same knowledge snapshot.

Checking service status…
01

Fastest way to connect

An MCP client with Streamable HTTP support needs only one URL.

https://doc.liz6.com/mcp 
{"mcpServers":{"liz6-docs":{"url":"https://doc.liz6.com/mcp"}}}

If your client does not support MCP, use OpenAPI, llms.txt, or append .md to any document URL.

02

Four access surfaces

The same public knowledge, adapted to different hosts and automation workflows.

MCP

Five read-only tools, document Resources, three workflow Prompts, and an MCP App for browsing results.

Checking
HTTP / OpenAPI

For scripts, workflow platforms, and Agents without MCP; supports lexical, semantic, and hybrid retrieval.

Checking
WebMCP

Compatible browsers discover the tools registered by each page; ordinary browsers remain unchanged.

Checking
Markdown

Source text preserves structure and metadata for lightweight fetching, citation, and long-context reading.

Available
03

Available capabilities

Tool descriptions clearly mark public, read-only, and untrusted-content boundaries.

search_documents

Combines full-text and multilingual semantic retrieval with compact plain-text excerpts.

list_documents

Browse by language, area, and tag with stable cursors.

read_document

Read Markdown, metadata, and the full outline.

read_document_section

Read a bounded section by heading to control context size.

related_documents

Find related documents through shared tags.

04

How browser Agents use it

On any page, a WebMCP-capable Chrome Agent can see all five tools directly—no URL copying required.

  1. The Agent opens any page on this site.
  2. The browser reads the WebMCP registration and capability manifest.
  3. The Agent searches, reads sources, and continues on the page.

WebMCP is progressively enabled through the Chromium Origin Trial; the MCP URL remains the more stable choice for general external Agents.