Browserless MCP integration for AI agents.
Connect AI agents to Browserless through 3 structured actions, including fetch content, generate pdf, and take screenshot. Review authentication, inputs, wor…
- ACTION CONTRACTS
- 3
- 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 Browserless integration exposes
The Browserless Agent App exposes 3 provider-backed actions for developer tools and data work. Its current contract lets an authorized agent fetch fully rendered html content from browserless, generate a browserless pdf file and store it in local transit storage, and generate a browserless screenshot and store it in local transit storage. 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 Browserless account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real Browserless capabilities.
Showing 3 of 3 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
fetch_contentREVIEWFetch fully rendered HTML content from Browserless.
INPUTS: url / html / bestAttempt / gotoOptions / waitForEvent
generate_pdfREVIEWGenerate a Browserless PDF file and store it in local transit storage.
INPUTS: url / html / options / bestAttempt / gotoOptions
take_screenshotREVIEWGenerate a Browserless screenshot and store it in local transit storage.
INPUTS: url / html / options / bestAttempt / gotoOptions
INPUT CONTRACTS
Know what the action needs before it runs.
fetch_content
urlOPTIONAL- The public URL Browserless should navigate to.
htmlOPTIONAL- The inline HTML Browserless should render instead of navigating to a URL.
bestAttemptOPTIONAL- Whether Browserless should continue when asynchronous wait steps fail or time out.
gotoOptionsOPTIONAL- Navigation options forwarded to Browserless gotoOptions.
waitForEventOPTIONAL- A Browserless waitForEvent configuration.
generate_pdf
urlOPTIONAL- The public URL Browserless should render into a PDF.
htmlOPTIONAL- The inline HTML Browserless should render into a PDF.
optionsOPTIONAL- The PDF options forwarded to Browserless.
bestAttemptOPTIONAL- Whether Browserless should continue when asynchronous wait steps fail or time out.
gotoOptionsOPTIONAL- Navigation options forwarded to Browserless gotoOptions.
take_screenshot
urlOPTIONAL- The public URL Browserless should capture.
htmlOPTIONAL- The inline HTML Browserless should capture instead of navigating to a URL.
optionsOPTIONAL- The screenshot options forwarded to Browserless.
bestAttemptOPTIONAL- Whether Browserless should continue when asynchronous wait steps fail or time out.
gotoOptionsOPTIONAL- Navigation options forwarded to Browserless gotoOptions.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Fetch Content
Fetch fully rendered HTML content from Browserless. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
fetch_contentVerify with Generate Pdf
Generate a Browserless PDF file and store it in local transit storage. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
generate_pdfSAFETY BOUNDARY
Operate Browserless with explicit limits
- Authorize Browserless with API key and grant only the provider access required by the selected actions.
- The current action names appear read-oriented, but returned Browserless data may still be sensitive and should be minimized before it enters model context.
- 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 Browserless rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the Browserless task completed successfully.
CONNECTION MODEL
API key
Browserless API token appended as the token query parameter. Create or copy it from the Browserless dashboard and REST API quickstart: https://docs.browserless.io/rest-apis/intro.
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
- 0
- WRITE SIGNALS
- 0
- HIGH IMPACT
- 0
- REVIEW SIGNALS
- 3
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 Browserless.