CONNECT APP
Build with Browser Use
Artificial Intelligence (AI)
- API key
MCP
Give your agent Browser Use tools
Every Browser Use 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 Browser Use 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": "browser_use",
},
},
},
)
const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)
const { tools } = await mcp.listTools()
// e.g. run Create Browser Session:
const result = await mcp.callTool({
name: "browser_use-create-browser-session",
arguments: {
profileId: "Profile ID",
proxyCountryCode: "Proxy Country Code",
},
})# 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": "browser_use",
}
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 Create Browser Session:
result = await session.call_tool("browser_use-create-browser-session", {
"profileId": "Profile ID",
"proxyCountryCode": "Proxy Country Code",
})API PROXY
Call the Browser Use API directly
For an endpoint with no pre-built tool, the Connect proxy forwards your request to the Browser Use 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.browser-use.com/api/v1/tasks",
})
// Any allowed Browser Use 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.browser-use.com/api/v1/tasks
curl "https://api.pipedream.com/v1/connect/{project_id}/proxy/aHR0cHM6Ly9hcGkuYnJvd3Nlci11c2UuY29tL2FwaS92MS90YXNrcw?external_user_id={external_user_id}&account_id=apn_xxxxxxx" \
-H "Authorization: Bearer {access_token}" \
-H "x-pd-environment: production"SDK
Run Browser Use actions from your backend
Connect a user's Browser Use account once, then run Create Browser Session 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: "browser_use-create-browser-session",
externalUserId: "{external_user_id}", // any stable ID for this user in your system
configuredProps: {
browser_use: { authProvisionId: "apn_xxxxxxx" },
profileId: "Profile ID",
proxyCountryCode: "Proxy Country Code",
},
})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="browser_use-create-browser-session",
external_user_id="{external_user_id}", # any stable ID for this user in your system
configured_props={
"browser_use": {"authProvisionId": "apn_xxxxxxx"},
"profileId": "Profile ID",
"proxyCountryCode": "Proxy Country Code",
},
)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": "browser_use-create-browser-session",
"configured_props": {
"browser_use": { "authProvisionId": "apn_xxxxxxx" },
"profileId": "Profile ID",
"proxyCountryCode": "Proxy Country Code"
}
}'TOOLS
Browser Use actions
On-demand operations your product or agent can configure and run on behalf of a connected user.
-
Create Browser Session
actionCreate a standalone Browser Use browser session for direct browser control through CDP. Browser sessions are billed by runtime and can run up to 4 hours. See the documentationWritev0.0.2 -
Create Profile
actionCreate a Browser Use profile to preserve cookies, local storage, and login state across sessions. See the documentationWritev0.0.2 -
Create Session
actionCreate an agent session, dispatch a task, or dispatch a follow-up task to an existing idle session. See the documentationWritev0.0.2 -
Create Workspace
actionCreate a Browser Use workspace for persistent shared file storage across sessions. See the documentationWritev0.0.1 -
Delete Profile
actionDelete a Browser Use profile. This removes persisted browser state for that profile. See the documentationWritev0.0.1 -
Delete Session
actionDelete an agent session. See the documentationWritev0.0.1 -
Delete Workspace
actionDelete a Browser Use workspace and its stored files. This cannot be undone. See the documentationWritev0.0.1 -
Delete Workspace File
actionDelete a file from a Browser Use workspace. See the documentationWritev0.0.1 -
Get Account Billing
actionGet Browser Use account billing details for the authenticated project. See the documentationRead-onlyv0.0.1 -
Get Browser Session
actionGet details for a standalone Browser Use browser session, including live URL, CDP URL, status, timeout, and cost fields. See the documentationRead-onlyv0.0.1 -
Get Profile
actionGet a Browser Use profile by ID. See the documentationRead-onlyv0.0.1 -
Get Session
actionGet the current state, output, live URL, screenshot URL, and cost details for an agent session. See the documentationRead-onlyv0.0.1 -
Get Workspace
actionGet a Browser Use workspace by ID. See the documentationRead-onlyv0.0.1 -
Get Workspace Size
actionGet storage usage for a Browser Use workspace. See the documentationRead-onlyv0.0.1 -
List Browser Sessions
actionList standalone Browser Use browser sessions for direct browser control via CDP. See the documentationRead-onlyv0.0.1 -
List Profiles
actionList Browser Use profiles, optionally searching by profile name or user ID. See the documentationRead-onlyv0.0.1 -
List Session Messages
actionList messages from a Browser Use agent session, including reasoning, tool calls, browser actions, screenshots, and results. See the documentationRead-onlyv0.0.1 -
List Sessions
actionList Browser Use agent sessions for the authenticated project. See the documentationRead-onlyv0.0.1 -
List Workspace Files
actionList files and folders in a Browser Use workspace, optionally returning presigned download URLs. See the documentationRead-onlyv0.0.1 -
List Workspaces
actionList Browser Use workspaces for persistent shared file storage across sessions. See the documentationRead-onlyv0.0.1 -
Stop Session
actionStop the current task or stop the entire Browser Use agent session. See the documentationWritev0.0.2 -
Update Browser Session
actionUpdate a standalone Browser Use browser session. Currently, Browser Use supports thestopaction. See the documentationWritev0.0.2 -
Update Profile
actionUpdate a Browser Use profile name or user ID. See the documentationWritev0.0.1 -
Update Workspace
actionUpdate a Browser Use workspace name. See the documentationWritev0.0.1 -
Upload Workspace Files
actionCreate presigned upload URLs for Browser Use workspace files, and optionally upload local Pipedream files to those URLs. See the documentationWritev0.0.2
EVENTS
Browser Use triggers
Event sources your backend can deploy for users and receive through a webhook.
No Browser Use triggers are available yet.
- App slug
- browser_use
- Authentication
- API key
- Categories
- Artificial Intelligence (AI)
- Actions
- 25
- Triggers
- 0
- API proxy
- Available