Browser Use
MCP Server Browser Use enables AI assistants to interact with web browsers through a FastAPI server, providing capabilities for web browsing, content extraction, and automation. Built by Igor Tarasenko and Martin Jakobsson, it leverages the browser-use library to perform tasks like navigating websites, extracting information, and taking screenshots. The server can be configured to use various LLM providers including OpenAI, OpenRouter, and Ollama, and can run in either headless or visible browser mode. It's particularly useful for workflows requiring web research, data collection, or automated interactions with web applications.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- browser-automation
- Source
- PulseMCP
- Repository
- github.com/deploya-labs/mcp-browser-use
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Browser Use from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp --scope user for --scope project to commit it to .mcp.json.