classify
Zero-shot classification for text.
LABSCO SUMMARY
Having segment, embeddings and rerank in one place means an entire retrieval pipeline is reachable without leaving the conversation.
Chunking, embedding and reranking are three steps that usually live in three libraries, and prototyping a retrieval approach means writing glue before learning anything. Exposing all three as calls makes the experiment conversational — try a chunk size, embed, rerank, see whether the right document surfaces. The reading tools serve a different purpose and are the more commonly used half: a page converted to something a model can actually read is worth more than raw HTML. get_help shipping the documentation as a tool is a small kindness that keeps parameter questions out of a browser.
What it is
A client for Jina AI's API surface covering retrieval infrastructure and web reading: embeddings and reranking, URL and search-result reading in a form built for models, a deep research mode, plus segmentation and classification.
What you get
- embeddings and rerank are the two halves of a retrieval pipeline — one to build the index, one to order what it returns.
- read turns a single URL into an LLM-friendly version of the page, and search does the same across the results for a term.
- deepsearch combines searching, reading and reasoning for an investigation rather than a lookup.
- segment splits text into segments or counts its tokens, which is the chunking step every retrieval pipeline needs.
- classify does zero-shot classification without a trained model.
- get_help returns the full Jina documentation, so the parameters are readable in place.
Requirements
JINA_API_KEY.
Setup effort
One command plus a key — npx -y jina-ai-mcp-server-nodejs, then supply credentials
USE CASES
01
Reading a page a model can actually use
Convert the URL to an LLM-friendly version rather than passing raw HTML, or do the same across a search term's results.
02
Researching something properly
Run the deep mode that searches, reads and reasons together, rather than issuing one query and summarising the first page.
03
Prototyping a retrieval pipeline
Chunk the text, embed the pieces, and rerank the results for a query — all three steps without writing glue.
04
Sorting text without training anything
Run zero-shot classification against the labels you care about.
8 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
deepsearch
Combines web searching, reading, and reasoning for comprehensive investigation.
embeddings
Creates an embedding vector representing the input text.
get_help
Returns the full content of the jina-docs.md documentation.
read
Input a single website URL and get an LLM-friendly version of that single website.
rerank
Reranks a list of documents based on a query.
search
Given a search term, get an LLM-friendly version of all websites in the search results.
segment
Given a text, splits it into segments or counts tokens.
BEFORE YOU INSTALL
What to know first
Tools you get
8 tools when we connected.
Requires
- npx on PATH
- JINA_API_KEY in your environment
CONTEXT COST
Light Standing cost
Rated by the size of the 8 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Add the block to your client, or run the command directly.
Server setup
Configuration file
JSON
{
"mcpServers": {
"jina-ai-mcp-server-nodejs": {
"command": "npx",
"args": [
"-y",
"jina-ai-mcp-server-nodejs"
]
}
}
}The configuration on this page does not set JINA_API_KEY; the project's instructions put it in a .env file. Check which folder the server reads that file from before you rely on it.
npx
TERMINAL
npx -y jina-ai-mcp-server-nodejs
