--- title: "Hyperbrowser MCP Server: review, setup & limitations · Undominated.ai" canonical: https://undominated.ai/mcp-servers/hyperbrowser/ description: "Scrape and crawl pages, extract structured web data and run hosted browser-agent sessions." --- # Hyperbrowser MCP Server: review, setup & limitations · Undominated.ai > Scrape and crawl pages, extract structured web data and run hosted browser-agent sessions. [← Explore all mcp servers](/mcp-servers/) BROWSER AUTOMATION / Hyperbrowser # Hyperbrowser MCP Server Scrape and crawl pages, extract structured web data and run hosted browser-agent sessions. [See setup guidance ↓](#setup)[Original source ↗](https://github.com/hyperbrowserai/mcp) SOURCE REVIEW Reviewed 2026-10-14 Evidence 4 linked sources Publisher Hyperbrowser Licence [MIT ↗](https://github.com/hyperbrowserai/mcp/blob/7492e83cf1825b3cf9725bfa25c5086df702599a/LICENSE) Revision 7492e83cf182 [Read what was—and wasn’t—checked ↓](#review) “Scrape and crawl pages, extract structured web data and run hosted browser-agent sessions.” [Hyperbrowser · upstream description ↗](https://github.com/hyperbrowserai/mcp/blob/7492e83cf1825b3cf9725bfa25c5086df702599a/README.md) Our analysis follows below. 01 / THE REASONING ## Why this made the selection. - Scrape and crawl pages, extract structured web data and run hosted browser-agent sessions. - The setup documentation makes this operating boundary explicit: Calls use the Hyperbrowser account and can create or delete persistent browser profiles; session content is processed by the hosted service. ### A good fit for - Scrape and crawl pages, extract structured web data and run hosted browser-agent sessions. - Run npx -y hyperbrowser-mcp with Node.js >=18 and HYPERBROWSER_API_KEY supplied through the client environment. Select a browser-agent or extraction tool for the target task. ### Weigh up before choosing - The Hyperbrowser API has features beyond this MCP surface. Persistent profiles retain session state; deletion is an active mutation, not a read operation. - Package/container parity with the pinned source and transitive dependency security were not established. 02 / THE REVIEW RECORD ## What we actually inspected. Source review has boundaries. A clear record is more useful than a “safe” badge. ### Material inspected - README.md - LICENSE - package.json - src/server.ts ### Our findings - Calls use the Hyperbrowser account and can create or delete persistent browser profiles; session content is processed by the hosted service. - The Hyperbrowser API has features beyond this MCP surface. Persistent profiles retain session state; deletion is an active mutation, not a read operation. ### Not established by this review - No server installation, authentication, live tool execution or isolation test was performed. - Package/container parity with the pinned source and transitive dependency security were not established. The review applies to the material and revision named here. A newer upstream release can change its behavior. 03 / PUT IT TO WORK ## Connect a server deliberately. [Upstream setup instructions ↗](https://github.com/hyperbrowserai/mcp/blob/7492e83cf1825b3cf9725bfa25c5086df702599a/README.md) DOCUMENTED COMMAND npx -y hyperbrowser-mcp Copy command ↗ Copying does not execute this command. It may retrieve a newer version than the reviewed source. - Run npx -y hyperbrowser-mcp with Node.js >=18 and HYPERBROWSER_API_KEY supplied through the client environment. Select a browser-agent or extraction tool for the target task. - Verify the connected account, available tools and target resource before authorizing mutations. ### Before you start - Pinned package Node.js requirement: >=18.0.0. - A compatible local process MCP client. - Calls use the Hyperbrowser account and can create or delete persistent browser profiles; session content is processed by the hosted service. ### Compatibility MCP clients that can launch the documented local process. ### Implementation TypeScript ### Transports stdio ### Local process with service or workstation access - Calls use the Hyperbrowser account and can create or delete persistent browser profiles; session content is processed by the hosted service. ### Cost model Publisher service entitlements, API usage and infrastructure charges apply where applicable; the MCP source licence does not include external services. 04 / FOLLOW THE EVIDENCE ## The source trail. Our notes are separate from the original resource. Check upstream before adopting a new version. - [Pinned publisher README and migration notices ↗](https://github.com/hyperbrowserai/mcp/blob/7492e83cf1825b3cf9725bfa25c5086df702599a/README.md) Checked 2026-10-14 https://github.com/hyperbrowserai/mcp/blob/7492e83cf1825b3cf9725bfa25c5086df702599a/README.md Supports: description, setup, capabilities, review, limitations - [Licence text at the reviewed commit ↗](https://github.com/hyperbrowserai/mcp/blob/7492e83cf1825b3cf9725bfa25c5086df702599a/LICENSE) Checked 2026-10-14 https://github.com/hyperbrowserai/mcp/blob/7492e83cf1825b3cf9725bfa25c5086df702599a/LICENSE Supports: license - [Pinned package metadata ↗](https://github.com/hyperbrowserai/mcp/blob/7492e83cf1825b3cf9725bfa25c5086df702599a/package.json) Checked 2026-10-14 https://github.com/hyperbrowserai/mcp/blob/7492e83cf1825b3cf9725bfa25c5086df702599a/package.json Supports: install, language, review - [Pinned implementation inspected for launch or permission boundary ↗](https://github.com/hyperbrowserai/mcp/blob/7492e83cf1825b3cf9725bfa25c5086df702599a/src/server.ts) Checked 2026-10-14 https://github.com/hyperbrowserai/mcp/blob/7492e83cf1825b3cf9725bfa25c5086df702599a/src/server.ts Supports: review, install, access, limitations KEEP COMPARING ## Other approaches to consider. Related by category or shared topics. These are alternatives to inspect, not a measured quality order. [### Firefox DevTools MCP ↗ Automate and inspect a local Firefox browser through WebDriver BiDi and selectable tool presets.](/mcp-servers/firefox-devtools/)[### Cloudflare Playwright MCP ↗ A Worker-hosted Playwright MCP server for Cloudflare Browser Rendering.](/mcp-servers/cloudflare-playwright/)[### Playwright MCP ↗ Gives an assistant persistent browser tools for inspecting page structure, interacting with controls and collecting browser evidence.](/mcp-servers/playwright/) [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/) ## Continue your investigation - [Inspect resource evidence](/tools/) - [Choose a host](/agents/) - [Inspect reusable workflows](/skills/) - [Use Undominated data](/api/)