CONNECT APP

Build with Jina Reader

Convert a URL to LLM-friendly input, by simply adding r.jina.ai in front.

Artificial Intelligence (AI)

API key

Visit Jina Reader ↗ Start building

MCP

Give your agent Jina Reader tools

Every Jina Reader action is exposed as an MCP tool on Pipedream's remote server. Point a client at it with your end user's ID and Connect resolves that user's Jina Reader account for each tool call — you store no tokens.

Pipedream Connect

// accessToken: mint a short-lived token with the Connect SDK — see the MCP guide
const transport = new StreamableHTTPClientTransport(
  new URL("https://remote.mcp.pipedream.net/v3"),
  {
    requestInit: {
      headers: {
        Authorization: `Bearer ${accessToken}`,
        "x-pd-project-id": "{project_id}",
        "x-pd-environment": "production",
        "x-pd-external-user-id": "{external_user_id}", // any stable ID for this user in your system
        "x-pd-app-slug": "jina_reader",
      },
    },
  },
)

const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)

const { tools } = await mcp.listTools()

// e.g. run Convert URL To LLM-Friendly Input:
const result = await mcp.callTool({
  name: "jina_reader-convert-to-llm-friendly-input",
  arguments: {
    url: "URL",
    contentFormat: "Content Format",
  },
})

# access_token: mint a short-lived token with the Connect SDK — see the MCP guide
headers = {
    "Authorization": f"Bearer {access_token}",
    "x-pd-project-id": "{project_id}",
    "x-pd-environment": "production",
    "x-pd-external-user-id": "{external_user_id}",  # any stable ID for this user in your system
    "x-pd-app-slug": "jina_reader",
}

async with streamablehttp_client("https://remote.mcp.pipedream.net/v3", headers=headers) as (read, write, _):
    async with ClientSession(read, write) as session:
        await session.initialize()
        tools = await session.list_tools()

        # e.g. run Convert URL To LLM-Friendly Input:
        result = await session.call_tool("jina_reader-convert-to-llm-friendly-input", {
            "url": "URL",
            "contentFormat": "Content Format",
        })

MCP guide →

API PROXY

Call the Jina Reader API directly

For an endpoint with no pre-built tool, the Connect proxy forwards your request to the Jina Reader API with the connected user's credentials attached. You store no tokens and write no refresh logic.

Pipedream Connect

const resp = await pd.proxy.get({
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  accountId: "apn_xxxxxxx",
  url: "https://r.jina.ai/https%3A%2F%2Fpipedream.com",
})

// Any allowed Jina Reader endpoint works here. Pipedream attaches the
// connected account's credentials to the outgoing request.

# The path segment is the target URL, URL-safe base64 encoded:
# https://r.jina.ai/https%3A%2F%2Fpipedream.com

curl "https://api.pipedream.com/v1/connect/{project_id}/proxy/aHR0cHM6Ly9yLmppbmEuYWkvaHR0cHMlM0ElMkYlMkZwaXBlZHJlYW0uY29t?external_user_id={external_user_id}&account_id=apn_xxxxxxx" \
  -H "Authorization: Bearer {access_token}" \
  -H "x-pd-environment: production"

API proxy guide →

SDK

Run Jina Reader actions from your backend

Connect a user's Jina Reader account once, then run Convert URL To LLM-Friendly Input on their behalf from your own code — TypeScript, Python, or plain HTTP.

Pipedream Connect

import { PipedreamClient } from "@pipedream/sdk"

const pd = new PipedreamClient({
  projectId: process.env.PIPEDREAM_PROJECT_ID!,
  clientId: process.env.PIPEDREAM_CLIENT_ID!,
  clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
  projectEnvironment: "production",
})

const result = await pd.actions.run({
  id: "jina_reader-convert-to-llm-friendly-input",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    jina_reader: { authProvisionId: "apn_xxxxxxx" },
    url: "URL",
    contentFormat: "Content Format",
  },
})

from pipedream import Pipedream

pd = Pipedream(
    client_id="{oauth_client_id}",
    client_secret="{oauth_client_secret}",
    project_id="{project_id}",
    project_environment="production",
)

result = pd.actions.run(
    id="jina_reader-convert-to-llm-friendly-input",
    external_user_id="{external_user_id}",  # any stable ID for this user in your system
    configured_props={
        "jina_reader": {"authProvisionId": "apn_xxxxxxx"},
        "url": "URL",
        "contentFormat": "Content Format",
    },
)

curl -X POST https://api.pipedream.com/v1/connect/{project_id}/actions/run \
  -H "Content-Type: application/json" \
  -H "X-PD-Environment: production" \
  -H "Authorization: Bearer {access_token}" \
  -d '{
    "external_user_id": "{external_user_id}",
    "id": "jina_reader-convert-to-llm-friendly-input",
    "configured_props": {
      "jina_reader": { "authProvisionId": "apn_xxxxxxx" },
      "url": "URL",
      "contentFormat": "Content Format"
    }
  }'