CONNECT APP
Build with Yutori
Build with Yutori’s state-of-the-art web agents that can autonomously monitor and execute tasks on the web.
Artificial Intelligence (AI)
- API key
MCP
Give your agent Yutori tools
Every Yutori 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 Yutori account for each tool call — you store no tokens.
// 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": "yutori",
},
},
},
)
const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)
const { tools } = await mcp.listTools()
// e.g. run Get Browsing Task Result:
const result = await mcp.callTool({
name: "yutori-get-browsing-task-result",
arguments: {
taskId: "Task ID",
},
})# 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": "yutori",
}
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 Get Browsing Task Result:
result = await session.call_tool("yutori-get-browsing-task-result", {
"taskId": "Task ID",
})API PROXY
Call the Yutori API directly
For an endpoint with no pre-built tool, the Connect proxy forwards your request to the Yutori API with the connected user's credentials attached. You store no tokens and write no refresh logic.
const resp = await pd.proxy.get({
externalUserId: "{external_user_id}", // any stable ID for this user in your system
accountId: "apn_xxxxxxx",
url: "https://api.yutori.com/v1/usage",
})
// Any allowed Yutori 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://api.yutori.com/v1/usage
curl "https://api.pipedream.com/v1/connect/{project_id}/proxy/aHR0cHM6Ly9hcGkueXV0b3JpLmNvbS92MS91c2FnZQ?external_user_id={external_user_id}&account_id=apn_xxxxxxx" \
-H "Authorization: Bearer {access_token}" \
-H "x-pd-environment: production"SDK
Run Yutori actions from your backend
Connect a user's Yutori account once, then run Get Browsing Task Result on their behalf from your own code — TypeScript, Python, or plain HTTP.
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: "yutori-get-browsing-task-result",
externalUserId: "{external_user_id}", // any stable ID for this user in your system
configuredProps: {
yutori: { authProvisionId: "apn_xxxxxxx" },
taskId: "Task ID",
},
})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="yutori-get-browsing-task-result",
external_user_id="{external_user_id}", # any stable ID for this user in your system
configured_props={
"yutori": {"authProvisionId": "apn_xxxxxxx"},
"taskId": "Task ID",
},
)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": "yutori-get-browsing-task-result",
"configured_props": {
"yutori": { "authProvisionId": "apn_xxxxxxx" },
"taskId": "Task ID"
}
}'TOOLS
Yutori actions
On-demand operations your product or agent can configure and run on behalf of a connected user.
-
Get Browsing Task Result
actionFetch the current status and result of a browsing task started with Run Browsing Task. Place a Delay step (15 minutes recommended) before this action to give the task time to complete. If the task is still running, the step returns the current status — re-run or increase the delay if needed. See the documentationRead-onlyv0.0.2 -
Get Research Task Result
actionFetch the current status and result of a research task started with Run Research Task. Place a Delay step (15 minutes recommended) before this action to give the task time to complete. Research tasks typically take 5–15 minutes. If the task is still running, the step returns the current status — re-run or increase the delay if needed. See the documentationRead-onlyv0.0.2 -
Get Scout
actionFetch the details and current status of a specific Yutori Scout by its ID. Returns the scout's configuration, status (active, paused, completed), and metadata. See the documentationRead-onlyv0.0.2 -
Get Scout Updates
actionFetch the latest findings from a specific Yutori Scout. Returns updates in reverse chronological order. Use the New Scout Update trigger for event-driven workflows; use this action when you need to pull findings on demand. See the documentationRead-onlyv0.0.2 -
Run Browsing Task
actionUse Yutori's cloud browser agent to navigate a website, fill forms, extract data, or complete any multi-step task — just describe it in plain English. Returns a task ID immediately; provide a Webhook URL to receive the full result the moment the task finishes. See the documentationWritev0.0.2 -
Run Research Task
actionUse Yutori to run deep web research across 100+ sources and get a comprehensive findings report — competitive analysis, market research, pricing comparisons, and more. Returns a task ID immediately; provide a Webhook URL to receive the full findings the moment research completes. See the documentationWritev0.0.2
- App slug
- yutori
- Authentication
- API key
- Categories
- Artificial Intelligence (AI)
- Actions
- 6
- Triggers
- 1
- API proxy
- Available