- CollectionBrowser & Web Execution
- Classificationagent-native
- MCPAvailable
- Agent SkillUnavailable
- InterfacesMCP · REST · SDK · http · API
What it does
Hyperbrowser is web infrastructure for AI agents: managed browsers, scraping/crawling, structured extraction, and multi-agent backends (browser-use, OpenAI CUA, Claude computer-use) behind one API. HyperAgent is the platform’s agent SDK. The MCP server exposes these capabilities directly to LLM clients so agents can research, extract, and automate the web without custom middleware.
Agent-facing interfaces
- Interaction pattern: REST API + SDKs + MCP
- Catalog protocols: MCP, REST, SDK, http, API
- MCP: ✅ Available
- Agent Skill: ⚠️ No official npx skills add hyperbrowser/… skill registry entry documented here.
- Onboarding type:
mcp
How agents onboard
Interaction pattern: REST API + SDKs + MCP
npx hyperbrowser-mcp <YOUR-HYPERBROWSER-API-KEY>
See the full onboarding section in the dossier.
Protocol surface
| Interface | Detail |
|---|---|
| REST | https://api.hyperbrowser.ai (see docs) |
| MCP | hyperbrowserai/mcp |
| Python | https://github.com/hyperbrowserai/python-sdk |
| Node.js | https://github.com/hyperbrowserai/node-sdk |