read_url
Pack: jina-reader · Connect: https://pipeworx.io/mcp (see Connect below for a single-pack URL)
No MCP client? Call it directly: GET https://gateway.pipeworx.io/v1/tools/read_url for the schema, then POST the same URL with its arguments for the data.
Any web page as clean markdown with navigation and ads stripped, via Jina Reader.
Tool description as the model sees it
Fetch any web page as clean, LLM-ready markdown (strips nav/ads) — ideal for giving an agent the readable content of a URL.
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
url | string | yes | The full target URL to fetch, e.g. “https://example.com/article”. |
Example call
curl -X POST https://gateway.pipeworx.io/jina_reader/mcp \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"read_url","arguments":{}}}'Connect
Add this to your MCP client config — every tool in the catalog, including this one — or use one-click install buttons:
{
"mcpServers": {
"pipeworx": {
"url": "https://pipeworx.io/mcp"
}
}
}Connect to just the jina-reader pack
{
"mcpServers": {
"jina-reader": {
"url": "https://gateway.pipeworx.io/jina_reader/mcp"
}
}
}See Getting Started for client-specific install steps.