Jina Reader
live AI/MLDeveloperJina Reader API: fetch any web page as clean LLM-ready markdown and run AI-optimized web searches returning markdown results.
2 tools
0ms auth
free tier 50 calls/day
Tools
read_url Fetch any web page as clean, LLM-ready markdown (strips nav/ads) — ideal for giving an agent the readable content of a URL.
No parameters required.
Try it
Response
search Web search returning the top results as markdown. Higher-volume usage may require your own Jina API key (pass via _apiKey).
No parameters required.
Try it
Response
Test with curl
The gateway speaks JSON-RPC 2.0 over HTTP POST. You can test any pack directly from the terminal.
List available tools
bash
curl -X POST https://gateway.pipeworx.io/jina_reader/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' Call a tool
bash
curl -X POST https://gateway.pipeworx.io/jina_reader/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"read_url","arguments":{}}}' Use with the SDK
Install @pipeworx/sdk to call tools from any TypeScript/Node project.
TypeScript
import { Pipeworx } from '@pipeworx/sdk';
const px = new Pipeworx();
const result = await px.call("read_url", {}); ask_pipeworx
// Or ask in plain English:
const answer = await px.ask("jina reader api: fetch any web page as clean llm-ready markdown and run ai-optimized web searches returning markdown results");