Jina AI

A workflow step names the app and the action, and the editor fills in the connection when you pick one. This is the Step shape from the workflow spec, carrying Jina AI's real ids.

{
  "manifestVersion": "2",
  "name": "jinaai-example",
  "steps": [
    {
      "id": "batch-embeddings-create",
      "uses": {
        "app": "io.w6w.jinaai",
        "action": "batch-embeddings-create",
        "connection": "conn_YOUR_CONNECTION_ID"
      },
      "with": {
        "model": "<model>"
      }
    }
  ]
}

Here are some of the things you can do

• Create Batch Embedding Job

  perform
  batch-embeddings-create

• Download Batch Errors

  read
  batch-errors-get

• Get Batch Job Status

  read
  batch-get

• Download Batch Output

  read
  batch-output-get

• List Batch Jobs

  read
  batches-list

+10 more actions available

Every app-specific value here is a blank you have to fill in. An app action is reached through the connection that authenticates it, so the address is a connection id, not the app id — and connections belong to your account, so a public page cannot know yours. Create one for Jina AI, then fill in the three blanks: conn_YOUR_CONNECTION_ID, the action key, and the parameters that action declares. The call itself is real — the shape is transcribed from the studio's own snippet builder, which prints the same kind of blanks — but nothing in it is specific to Jina AI. The Workflow tab is where this app's real ids are.

npm install @w6w/sdk

yarn add @w6w/sdk

pnpm add @w6w/sdk

deno add npm:@w6w/sdk

import { W6wClient, isActionRun } from "@w6w/sdk";

// Reads W6W_BASE_URL and W6W_TOKEN from the environment when omitted.
const client = new W6wClient();

const envelope = await client.run({
  urn: "conn_YOUR_CONNECTION_ID",
  action: "batch-embeddings-create",
  payload: {
    model: "<value>",
    // inputUrl: "<value>",
    // input: "<value>",
    // task: "<value>",
    // dimensions: "<value>",
    // normalized: "<value>",
    // webhookUrl: "<value>",
  },
});

if (isActionRun(envelope)) console.log(envelope.value);

npm install -g @w6w/cli

w6w run conn_YOUR_CONNECTION_ID --action batch-embeddings-create --payload '{"model":"<value>"}'

Give an AI agent Jina AI — without giving it Jina AI's credentials. One MCP endpoint exposes every app, function and workflow the caller is entitled to, as tools it can discover and run. Access is granted per team while we onboard.

{
  "name": "w6w_invoke",
  "arguments": {
    "ref": "app:io.w6w.jinaai#batch-embeddings-create",
    "input": {
      "model": "<model>"
    }
  }
}

Every tool names its target with a single ref. The app: form above doesn't name a connection at all — the host resolves which of the caller's Jina AI connections to sign with, and refuses rather than guesses when the answer is ambiguous.

What the agent gets

The MCP surface is part of the hosted platform. Jina AI itself is MIT, and the runtime that executes it is source-available (FSL).

Request MCP access