mcpField
J
Jina Reader

Jina Reader

Remote
pipeworx.ioBrowser Automation0Updated 2d ago

About Jina Reader

Jina Reader is an MCP server for extracting web pages and searching the web. It returns cleaned page content and search results as Markdown, and runs through the Pipeworx gateway or locally over stdio; calls require a Jina API key.

Key features

  1. 01Convert web pages to clean Markdown
  2. 02Search the web with Markdown results

Use cases

  1. 01Prepare page text for LLM reading
  2. 02Strip navigation, ads, and boilerplate
  3. 03Search the web and process results

MCP support

It exposes page-reading and web-search tools to MCP clients. It supports the Pipeworx gateway or local stdio; a Jina API key is required, and gateway connections also include shared meta-tools.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://gateway.pipeworx.io/jina-reader/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

@pipeworx/jina-reader

Turn any URL into clean, LLM-ready markdown, plus web search — via Jina AI Reader.

Part of Pipeworx — an MCP gateway connecting AI agents to 1882+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

ToolWhat it answers
read_urlThe readable content of a web page as markdown, with nav/ads/boilerplate stripped.
searchTop web-search results for a query, returned as markdown.

Auth

A Jina API key is required. Jina retired its anonymous tier — both r.jina.ai and s.jina.ai now answer an unauthenticated request with 401 AuthenticationRequiredError. The pack shipped in June 2026 as keyless and that is no longer true of the upstream.

  • Platform key: PLATFORM_JINA_KEY, injected by the gateway as _apiKey. Provisioned and live since 2026-09-01 (search verified live against the deployed gateway that day, fleet #719) — callers need no key of their own. It is a FREE key on a fixed token grant, not a monthly reset, so the expected end state is the balance running out rather than the key expiring.
  • BYO: pass _apiKey on the call. Free keys at https://jina.ai/reader.

Jina's 401 bodies are distinct and worth reading before assuming a key expired:

BodyMeans
AuthenticationRequiredError: Authentication is required to use this endpointno key was sent at all
AuthenticationFailedError: Invalid API keythe key sent is wrong or revoked
AuthenticationRequiredError: … bad network reputation (ASnnnn)anonymous call from a blocked network

A 402 is none of the above: the key is valid and its token balance is spent. The pack says so in those words, and the gateway books it as platform_quota_exhausted — a purchase, not a key to rotate and not a Jina outage. Before 2026-09-01 that status fell through to upstream_down, which would have read as the vendor being broken.

Data sources

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "jina-reader": {
      "url": "https://gateway.pipeworx.io/jina-reader/mcp"
    }
  }
}
What this endpoint actually serves

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 1882+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

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":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "jina-reader": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-jina-reader"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-jina-reader

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

Using with ask_pipeworx

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.

More

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.