/docs / integrations
For agent developers
Integrations: MCP, SDKs, reader
Plug Lyrenth in as your agent's web reader. One key works across every surface below, each returns the same clean AIDocument.
›
MCP server
Adds a read_url tool to Claude Desktop, Claude Code, Cursor, or any MCP client. Drop this into your client's MCP config:
claude_desktop_config.json
{
"mcpServers": {
"lyrenth": {
"command": "npx",
"args": ["-y", "lyrenth-mcp"],
"env": { "LYRENTH_API_KEY": "your-key" }
}
}
}›_
Reader endpoint
One authenticated GET returns clean Markdown, a shell one-liner, or any HTTP client.
curl "https://api.lyrenth.com/v1/read?url=https://example.com/post" \ -H "Authorization: Bearer $LYRENTH_API_KEY"
py
Python SDK
A dependency-free client, plus LangChain and LlamaIndex adapters.
pip install lyrenth
from lyrenth import Lyrenth
client = Lyrenth(api_key="lyr_live_…")
doc = client.aidocument("https://example.com/post")
print(doc.content.markdown)RAG adapters
pip install 'lyrenth[langchain]' # LyrenthLoader pip install 'lyrenth[llamaindex]' # LyrenthReader
ts
TypeScript SDK
A dependency-free client, plus a ready-made tool for the Vercel AI SDK.
npm install lyrenth-sdk
import { Lyrenth } from "lyrenth-sdk";
const client = new Lyrenth({ apiKey: process.env.LYRENTH_API_KEY });
const doc = await client.aidocument("https://example.com/post");
console.log(doc.content.markdown);▲
Vercel AI SDK tool
A read_url tool the model can call mid-generation to pull a clean page into context.
import { lyrenthTool } from "lyrenth-sdk/ai";
const result = await generateText({
model: openai("gpt-4o"),
tools: { read_url: lyrenthTool(process.env.LYRENTH_API_KEY) },
prompt: "Summarize https://example.com/post",
});