What can you do with the Jina AI integration?

LiveContext exposes 6 operations on Jina AI, covering classification, embedding, page and ranking. Common uses include routing inbound messages by intent, indexing documents for semantic search and one-shot research grounding for an agent.

LiveContext

All integrations

Jina AI integration

Jina AI foundation APIs for retrieval pipelines: turn any URL into clean LLM-ready markdown with Reader, search the web and get the full page text back, embed text or images with jina-embeddings, rerank candidates with jina-reranker, split long documents into semantic chunks, classify with zero-shot labels, and fact-check a statement with Grounding.

6 toolsTokenAPI docs

Connect Jina AI How integrations work

Common Jina AI use cases

routing inbound messages by intent
indexing documents for semantic search
one-shot research grounding for an agent
preparing long documents for an embedding step
feeding a web page into an LLM without HTML noise
improving RAG precision before the generation step
building a RAG corpus from a query
scraping a JavaScript-rendered site
counting tokens before an expensive call
tagging content without a labelled dataset

What you can do with Jina AI

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Classification, 1 operation

POSTclassify
Classifies text or images against labels given at call time, zero-shot.

Embedding, 1 operation

POSTcreate_embeddings
Creates text or image embeddings with the jina-embeddings models.

Page, 1 operation

POSTread_url
Converts any web page into clean LLM-ready markdown.

Ranking, 1 operation

POSTrerank
Reranks candidate documents against a query with a cross-encoder.

Search result, 1 operation

POSTsearch_web
Searches the web and returns the full page text of each result.

Segment, 1 operation

POSTsegment_text
Splits a long document into semantic chunks ready for embedding.

Use Jina AI from Claude Code, Cursor or Codex

Connect Jina AI in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Jina AI operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Jina AI

Create your workspace
Sign up free. Nothing to install.
Connect Jina AI once
Add your Jina AI connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Jina AI integration FAQ

What can you do with the Jina AI integration?: LiveContext exposes 6 operations on Jina AI, covering classification, embedding, page and ranking. Common uses include routing inbound messages by intent, indexing documents for semantic search and one-shot research grounding for an agent.