jina_reader
Read and extract content from web page.
LABSCO SUMMARY
Two tools, chosen on the grounds that every tool definition costs context before the work starts.
For a coding agent the web is usually a two-step affair — find a few pages, read the one that answers the question — and that is exactly what this exposes. The paginated reader is the practical difference from a plain fetch: an oversized documentation page arrives in slices with a cache behind it, instead of arriving all at once or not at all.
What it is
A deliberately small server on Jina AI Reader and Search: one tool finds a shortlist of pages, the other reads one page at a time.
What you get
- Web search returning a lightweight shortlist, with partial content per result so you can choose before you read
- Page reading that extracts the content of a URL, paginated by token count so a huge page arrives in manageable pieces
- An LRU cache holding 50 URLs by default, and roughly 15,000 tokens per reader page — both configurable
- A two-tool surface by design: no embeddings, reranking, image search or classification competing for the model's attention
- Either transport: stdio by default, or HTTP bound to localhost, with a bearer token and an origin allowlist for remote use
Requirements
Node.js 20 or later. Runs from npm as jina-mcp-tools. A Jina AI API key in JINA_API_KEY enables search; leave it out and you get reader-only mode, subject to Jina's unauthenticated rate limits. For HTTP mode beyond localhost, set JINA_MCP_HTTP_AUTH_TOKEN and put it behind TLS. This is a community project, not Jina's own server.
Setup effort
One command plus a key — npx -y jina-mcp-tools, then supply credentials
USE CASES
01
Checking how a library actually behaves
Search for the page, then read it in full instead of trusting the search snippet.
02
Reading a long documentation page without blowing the context
Pull it a page at a time at the token size you set, with the cache serving repeat reads.
03
Finding out what changed recently
Search the web from inside the coding session and open the two or three results worth opening.
04
Keeping web access when you have no key
Run reader-only and read URLs you already have, within the unauthenticated rate limits.
2 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
jina_search
Search the web. The response includes only partial contents of each web page. Use jina reader for full content.
BEFORE YOU INSTALL
What to know first
Tools you get
2 tools when we connected; the project documents 3. --search-endpoint picks one search tool: jina_search (standard, the default) or jina_search_vip, never both. Without JINA_API_KEY, only jina_reader is available.
Requires
- npx on PATH
- Node.js 20 or later
- JINA_API_KEY in your environment
INSTALLATION
Connect your client
Server setup
TERMINAL
npx -y jina-mcp-toolsMCP Clients
Codex
CODEX · TERMINAL
codex mcp add jina-web --env JINA_API_KEY="$JINA_API_KEY" -- npx -y jina-mcp-toolsClaude Code
CLAUDE CODE · TERMINAL
claude mcp add --scope user \
--env JINA_API_KEY="$JINA_API_KEY" \
--transport stdio jina-web -- npx -y jina-mcp-toolsVS Code
VS CODE · JSON
{
"inputs": [
{
"type": "promptString",
"id": "jina-api-key",
"description": "Jina AI API key",
"password": true
}
],
"servers": {
"jina-web": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"jina-mcp-tools"
],
"env": {
"JINA_API_KEY": "${input:jina-api-key}"
}
}
}
}Claude Desktop, Cursor, Other MCP clients
JSON
{
"mcpServers": {
"jina-web": {
"command": "npx",
"args": [
"-y",
"jina-mcp-tools"
],
"env": {
"JINA_API_KEY": "<YOUR_JINA_API_KEY>"
}
}
}
}
