Browser Use MCP integration for AI agents.
Connect AI agents to Browser Use through 6 structured actions, including get billing account, run task, and stop session. Review authentication, inputs, work…
- ACTION CONTRACTS
- 6
- AUTHENTICATION
- API key
- SOURCE STATUS
- Provider-backed
CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE
CAPABILITY PROFILE
What the Browser Use integration exposes
The Browser Use Agent App exposes 6 provider-backed actions for ai and developer tools work. Its current contract lets an authorized agent get browser use cloud account billing and plan information, create or reuse a browser use cloud session and dispatch an agent task, and stop a browser use cloud session or the current task in that session. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.
A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.
For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected Browser Use account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real Browser Use capabilities.
Showing 6 of 6 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_billing_accountREADGet Browser Use Cloud account billing and plan information.
run_taskWRITECreate or reuse a Browser Use Cloud session and dispatch an agent task.
INPUTS: task / model / sessionId / keepAlive / maxCostUsd
stop_sessionREVIEWStop a Browser Use Cloud session or the current task in that session.
INPUTS: sessionId / strategy
get_sessionREADGet a Browser Use Cloud session and poll for task completion.
INPUTS: sessionId
list_session_messagesREADList Browser Use Cloud messages for one session.
INPUTS: sessionId / after / before / limit
list_sessionsREADList Browser Use Cloud sessions for the authenticated project.
INPUTS: page / pageSize
INPUT CONTRACTS
Know what the action needs before it runs.
run_task
taskREQUIRED- The natural-language instruction for the Browser Use agent.
modelOPTIONAL- The Browser Use model to run the task with.
sessionIdOPTIONAL- The Browser Use session ID.
keepAliveOPTIONAL- Whether to keep the session alive after the task completes.
maxCostUsdOPTIONAL- Maximum total cost in USD allowed for this session.
stop_session
sessionIdREQUIRED- The Browser Use session ID.
strategyOPTIONAL- How Browser Use should stop the session.
get_session
sessionIdREQUIRED- The Browser Use session ID.
list_session_messages
sessionIdREQUIRED- The Browser Use session ID.
afterOPTIONAL- Return messages after this message ID.
beforeOPTIONAL- Return messages before this message ID.
limitOPTIONAL- The maximum number of messages to return.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Billing Account
Get Browser Use Cloud account billing and plan information. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_billing_accountControl Run Task
Create or reuse a Browser Use Cloud session and dispatch an agent task. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
run_taskVerify with Get Session
Get a Browser Use Cloud session and poll for task completion. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
get_sessionSAFETY BOUNDARY
Operate Browser Use with explicit limits
- Authorize Browser Use with API key and grant only the provider access required by the selected actions.
- 1 action is change-capable by name. Confirm the target identity and material parameters before allowing a write.
- Do not infer permission from catalog visibility. Workspace policy, connection identity, and upstream authorization still govern execution.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in Browser Use rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the Browser Use task completed successfully.
CONNECTION MODEL
API key
Browser Use Cloud API key sent with the X-Browser-Use-API-Key header. Create one from https://cloud.browser-use.com/settings?tab=api-keys&new=1.
Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.
- READ SIGNALS
- 4
- WRITE SIGNALS
- 1
- HIGH IMPACT
- 0
- REVIEW SIGNALS
- 1
EVIDENCE AND AVAILABILITY
Provider reference
Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by Browser Use.