Hyperbrowser MCP server
31 operations0 webhooks
Fast cloud browsers for AI agents, web scraping, multi-page crawling, searching, and structured data extraction.
Try Hyperbrowser with your agent
Connect Hyperbrowser, then paste this into Claude, ChatGPT or Cursor. For ideas from other apps, see the use cases.
Using Corsair, show me what you can do in Hyperbrowser on my account, then run one read-only example and show me the result.
Hyperbrowser tools and triggers
Tools are what your agent can do in Hyperbrowser through Corsair's MCP server. Triggers are the Hyperbrowser events a routine can start from.
Sessions
- CreateDestructive
Create and launch a cloud browser session (consumes compute credits)
sessions.create
- Evaluate CaptchaDestructive
Run CAPTCHA evaluation and solving on an active session (consumes credits)
sessions.evaluateCaptcha
- GetRead-only
Get cloud browser session details by ID
sessions.get
- Get Downloads UrlRead-only
Get the downloads archive URL for a browser session
sessions.getDownloadsUrl
- Get Recording UrlRead-only
Get the web recording replay URL for a browser session
sessions.getRecordingUrl
- Get Video Recording UrlRead-only
Get the video recording URL for a browser session
sessions.getVideoRecordingUrl
- ListRead-only
List cloud browser sessions with optional pagination and status filter
sessions.list
- StopWrite
Stop an active cloud browser session
sessions.stop
- UpdateWrite
Update live configuration of a running browser session
sessions.update
Crawl
- CreateRead-only
Start an asynchronous multi-page crawl job (consumes compute credits)
crawl.create
- Create WebRead-only
Start an asynchronous web crawl job using the Web API engine (consumes compute credits)
crawl.createWeb
- GetRead-only
Get crawl job status and crawled pages data by job ID
crawl.get
- Get StatusRead-only
Get the current status of an asynchronous crawl job by job ID
crawl.getStatus
- Get WebRead-only
Get web crawl job status and crawled page data by job ID
crawl.getWeb
- Get Web StatusRead-only
Get the current status of an asynchronous web crawl job by job ID
crawl.getWebStatus
Scrape
- CreateRead-only
Start an asynchronous web scrape job (consumes compute credits)
scrape.create
- Create BatchRead-only
Start an asynchronous batch scrape job across multiple URLs (consumes compute credits)
scrape.createBatch
- GetRead-only
Get scrape job status and content data by job ID
scrape.get
- Get BatchRead-only
Get results and page data of a batch scrape job by job ID
scrape.getBatch
- Get Batch StatusRead-only
Get the current status of an asynchronous batch scrape job by job ID
scrape.getBatchStatus
- Get StatusRead-only
Get the current status of an asynchronous scrape job by job ID
scrape.getStatus
Profiles
- CreateWrite
Create a new persistent browser profile
profiles.create
- DeleteDestructive
Permanently delete a persistent browser profile by ID
profiles.delete
- ForkWrite
Fork an existing persistent browser profile
profiles.fork
- GetRead-only
Get persistent browser profile details by ID
profiles.get
- ListRead-only
List persistent browser profiles with optional pagination and name filter
profiles.list
Extract
- CreateRead-only
Start an AI structured data extraction job across URLs (consumes compute credits)
extract.create
- GetRead-only
Get the extracted structured data and status of an extract job by job ID
extract.get
- Get StatusRead-only
Get the current status of an asynchronous extract job by job ID
extract.getStatus
Web
- FetchRead-only
Fetch web page content in multiple formats using cloud browser (consumes compute credits)
web.fetch
- SearchRead-only
Search the web with clean structured results (consumes compute credits)
web.search
Connect Hyperbrowser to Claude, ChatGPT or Cursor
- 1
Connect Hyperbrowser in Corsair
Add your Hyperbrowser API key once in Corsair. Corsair stores the credential encrypted and makes the Hyperbrowser API calls for your agent, so it never goes into a prompt or a config file. Connect Hyperbrowser
If your link lets the agent add apps, you can skip this: it gives you a sign-in link the first time it needs Hyperbrowser. On a ChatGPT personal plan, connect Hyperbrowser here first.
- 2
Add Corsair's MCP server to your agent
Every client uses the same address:
https://mcp.corsair.dev/mcpOpen Customize → Connectors → Add custom connector, paste the address, then select Connect.Add a custom MCP server with the address and choose OAuth. Personal plans get read tools only.Add to CursorOr add this to~/.cursor/mcp.json. Cursor opens Corsair to sign in the first time it connects.{ "mcpServers": { "corsair": { "url": "https://mcp.corsair.dev/mcp" } } }Run this, then run/mcpin Claude Code to sign in.claude mcp add --transport http corsair https://mcp.corsair.dev/mcpCodex, Gemini CLI, VS Code, Zed and other clients with OAuth sign-in work the same way. Clients without it, such as GitHub Copilot's coding agent, use a link's own address and an API key. Setup for every client
- 3
Sign in and choose what needs your approval
Your client opens Corsair to sign in. Pick a link: the apps your agent can use and a mode that decides what it may do without asking. In the default Cautious mode, Hyperbrowser's read and write operations run right away and its 3 destructive operations wait for your approval. Strict mode asks before every write and refuses destructive operations, and Read mode allows reads only.
FAQ
Install corsair and @corsair-dev/hyperbrowser, add the Hyperbrowser plugin, and connect with an API key. Then call methods like corsair.hyperbrowser.api.crawl.create() from your app. Corsair keeps each tenant isolated.
Yes. Hyperbrowser requires an API key from your Hyperbrowser account or developer dashboard. Create credentials with access that matches what you automate, then paste them into Corsair or connect through managed auth in Hub.
Yes. One Corsair client can hit Hyperbrowser, GitHub, Notion, Stripe, and the rest. Trigger Hyperbrowser from a webhook, push updates to Slack, or chain actions across plugins. Same tenant context across integrations, plain TypeScript.
Teams use Corsair for fast cloud browsers for AI agents, web scraping, multi-page crawling, searching, and structured data extraction. Common builds include sync jobs, admin tooling, and agents that call Hyperbrowser APIs from your backend.
The SDK is open source. Self-host and you pay Corsair nothing for the integration layer. Hub bills for hosted auth and execution, not per Hyperbrowser API call. Hub has a generous free tier. For hobby projects you can probably run the whole thing on free. Paid plans start to matter with more tenants or heavier traffic.
We maintain @corsair-dev/hyperbrowser in the open repo. When Hyperbrowser ships API changes, upgrade the package. Your call sites stay typed. You should not need to rewrite the integration layer each time.
No. Corsair does not read your Hyperbrowser data or hold individual access credentials. Credentials stay in your database. API calls run on your instance. We do not store Hyperbrowser data on your behalf.
Yes. Add https://mcp.corsair.dev/mcp as a custom connector or MCP server in Claude, ChatGPT, Cursor, VS Code, Claude Code, Codex or any client that supports remote MCP servers with OAuth sign-in, then sign in to Corsair. On ChatGPT personal plans, custom servers currently get read tools only.
Yes. Put Hyperbrowser on a link in Strict mode and every write waits for your approval, while destructive actions are refused. The default Cautious mode asks only before the 3 destructive Hyperbrowser operations. You can change a link's mode at hub.corsair.dev/me.