
This connects Claude to Jina AI's reader and search APIs via the Pipeworx gateway. The main use case is converting any URL into clean, LLM-friendly markdown that strips away navigation, ads, and formatting noise. You also get web search capabilities through the same interface. It's hosted remotely over streamable HTTP, so there's no local setup. You can use it standalone or tap into the full Pipeworx gateway for access to 700+ other data sources. The ask_pipeworx tool lets you query in natural language instead of calling specific endpoints. Reach for this when you need Claude to read web content or search without dealing with raw HTML parsing.
Jina AI Reader/Search MCP — turn any URL into clean LLM-ready markdown, plus web search.
Part of Pipeworx — an MCP gateway connecting AI agents to 1481+ live data sources.
| Tool | Description |
|---|---|
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. |
search | Web search returning the top results as markdown. Higher-volume usage may require your own Jina API key (pass via _apiKey). |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"jina_reader": {
"url": "https://gateway.pipeworx.io/jina_reader/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/jina_reader/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1481+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Jina Reader data" })
The gateway picks the right tool and fills the arguments automatically.
MIT
Our jina_reader key is reserved for paid accounts, so an anonymous call to POST https://gateway.pipeworx.io/v1/tools/read_url needs your own key passed as _apiKey alongside the arguments. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/read_url. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.