Browser automation MCP server that lets AI agents control cloud browser sessions through Browserbase and Stagehand for navigation, actions, observation, and extraction.
Open the source and read safety notes before installing.
Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.
Decision playbook
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
0
63
—
No baseline selected
No major trust-signal divergence detected in the current selection.
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Source provenance statusRequired
Marked as source-backed.
Metadata reviewed
No reviewed flag detected in metadata.
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Trust level risk gateRequired
Trust level does not block evaluation.
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Package verification flag
No package verification flag provided.
Checksum metadata
No checksum provided for downloaded artifact.
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
Baseline comparison available
No baseline peer selected yet.
Diverging trust signals identified
No major trust-signal divergence found.
Setup at a glance
Copy-ready — paste the snippet to get started.
Adoption plan
Current risk score 24/100. Use staged verification before broader rollout.
Validate source and review signals before any execution.
Confirm source provenanceRequired
Source URL/provenance metadata is present.
Confirm metadata review state
No review metadata found; increase manual validation.
Verify install payload
Install/config payload exists and can be inspected.
Confirm safety, privacy, and package integrity signals.
Review safety notesRequired
Safety notes are present.
Review privacy notesRequired
Privacy notes are present.
Verify package integrity metadata
No package verification/checksum metadata.
Adopt in controlled steps based on the selected plan.
Run in isolated sandbox firstRequired
Use a constrained sandbox and observe behavior across multiple tasks.
Roll out graduallyRequired
Roll out to a small cohort before wider usage.
Set monitoring and fallback
Define rollback path and monitor errors after adoption.
Evidence readiness
Missing required evidence: Metadata review. Risk score 31.
Source repository/provenance is listed.
Required in this preset
Review metadata is missing.
Required in this preset
Safety notes are present.
Required in this preset
Privacy notes are present.
Optional in this preset
Package integrity metadata is missing.
Optional in this preset
Install payload is available.
Required in this preset
Required gaps: Metadata review
Decision timeline
Blocking gaps: Check metadata review status. Risk 28.
triage
Source/provenance metadata is available.
triage
Review metadata is missing.
verify
Safety notes are available.
verify
Privacy notes are available.
verify
Package integrity metadata is missing.
rollout
Install payload is available.
Blockers: Check metadata review status
Prerequisite readiness
4 prerequisites to line up before setup. Have accounts and credentials ready first.
Safety & privacy surface
4 safety and 3 privacy notes across 5 risk areas. Review closely: credentials & tokens, permissions & scopes, third-party handling.
{
"mcpServers": {
"browserbase": {
"command": "npx",
"args": ["@browserbasehq/mcp"],
"env": {
"BROWSERBASE_API_KEY": "YOUR_BROWSERBASE_API_KEY",
"BROWSERBASE_PROJECT_ID": "YOUR_BROWSERBASE_PROJECT_ID",
"GEMINI_API_KEY": "YOUR_GEMINI_API_KEY"
}
}
}
}Browserbase MCP Server gives AI agents cloud browser automation through Browserbase and Stagehand. It exposes tools for starting or reusing a browser session, navigating to URLs, acting on pages, observing actionable elements, extracting data, and ending sessions.
The repository describes this project as the self-hostable version of
Browserbase's hosted MCP server, with support for hosted HTTP and self-hosted
stdio usage through the @browserbasehq/mcp npm package.
These sources were reviewed on 2026-06-05. Prefer the live docs for current hosted endpoint behavior, package name, Stagehand model options, Browserbase flags, and client-specific setup.
start, end, navigate, act, observe, and extract.For self-hosted stdio usage through npm:
{
"mcpServers": {
"browserbase": {
"command": "npx",
"args": ["@browserbasehq/mcp"],
"env": {
"BROWSERBASE_API_KEY": "YOUR_BROWSERBASE_API_KEY",
"BROWSERBASE_PROJECT_ID": "YOUR_BROWSERBASE_PROJECT_ID",
"GEMINI_API_KEY": "YOUR_GEMINI_API_KEY"
}
}
}
}
For clients with hosted MCP support, the docs also describe the hosted Browserbase MCP endpoint. Use the repository and Browserbase docs for current transport, key, and model-provider setup.
Cloud browser automation can affect real web accounts and third-party services. Keep sessions scoped, avoid high-volume automation unless authorized, and require review before submitting forms, making purchases, sending messages, changing account settings, or collecting personal data.
Treat Browserbase contexts, cookies, extracted page content, prompts, API keys, and model-provider traffic as sensitive. Review persisted-context settings before automating logged-in workflows.
No browserbase/mcp-server-browserbase entry or source URL was found in
content/mcp. This entry is separate from local browser-profile tools,
Playwright MCP, Chrome MCP, and BrowserMCP because it focuses on Browserbase
cloud sessions and Stagehand.
Show that Browserbase MCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/mcp/browserbase-mcp-server)Browserbase MCP Server side by side with its closest alternative on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
| Field | Browser automation MCP server that lets AI agents control cloud browser sessions through Browserbase and Stagehand for navigation, actions, observation, and extraction. Open dossier | AgentQL MCP server for extracting structured JSON from public webpages using a URL and natural-language extraction prompt. Open dossier |
|---|---|---|
| Next steps | ||
| Trust | ||
| Review status | Not reviewed | Not reviewed |
| Package trust | Package not verified | Package not verified |
| Source provenance | Source-backed | Source-backed |
| Submitter | oktofeesh1 | oktofeesh1 |
| Install risk | Review first | Review first |
| Notes | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ |
| Brand | ||
| Category | mcp | mcp |
| Source | Source-backed | Source-backed |
| Author | Browserbase | AgentQL |
| Added | 2026-06-05 | 2026-06-06 |
| Platforms | ||
| Harness | ||
| Source repo | — | — |
| Safety notes | ✓Browserbase MCP can create browser sessions, navigate URLs, perform page actions, observe actionable elements, extract data, and close sessions. Cloud browser automation can submit forms, change account state, trigger transactions, scrape sites, or violate website terms if not scoped. Require human approval before login, purchase, messaging, account-change, destructive, or high-volume browsing actions. Review proxy, verified identity, persisted context, and keep-alive options before using them with sensitive sites. | ✓AgentQL MCP exposes one tool, `extract-web-data`, that sends a target URL and natural-language extraction prompt to the AgentQL API. The tool is intended for public webpages; do not use it to bypass access controls, scrape private pages, evade paywalls, or extract data where automated collection is prohibited. Web extraction can still trigger target-site rate limits, legal restrictions, robots guidance, or terms-of-service concerns. The source implementation uses AgentQL's query-data endpoint with fast mode, no screenshot capture, no scroll-to-bottom behavior, and no local browser cookies. Treat extracted output as untrusted web data that may include errors, stale content, ads, tracking text, or prompt-injection attempts. |
| Privacy notes | ✓Browser session URLs, page content, extracted data, screenshots or observations, cookies or persisted context, API keys, and prompts may be sent to Browserbase, Stagehand/model providers, and the MCP client. Persisted browser contexts can retain login state, cookies, and site data across sessions. Protect Browserbase, project, and model-provider keys in config files, logs, screenshots, and shared prompts. | ✓Target URLs, extraction prompts, API key-authenticated requests, and extracted structured data are sent to AgentQL's API. Extracted data can include personal data, copyrighted content, customer information, job postings, prices, social content, or other third-party material. AGENTQL_API_KEY should stay out of prompts, issues, logs, screenshots, and committed configuration files. Claude transcripts and downstream reports may retain extracted data, so avoid collecting information that is not approved for the model session. |
| Prerequisites |
|
|
| Install | | |
| Config | | |
| Citations | ||
| Claim | Unclaimed | Unclaimed |
Source-backed guides for putting this to work.
Set autoMode.hard_deny rules to block risky actions in auto mode.
Loading live community signals…
A short, calm digest of reviewed Claude resources. Unsubscribe any time.