Browser Automation
The MCP Browser Agent enables Claude to interact with web browsers through the Model Context Protocol, built during the AGI House MCP Hackathon by Jaeyun and Ashley Ha. It leverages the browser-use library to provide a seamless integration that allows Claude to automate browser interactions, detect interactive elements, and execute planned actions. The implementation includes two main tools: one for retrieving the current browser state and planning context, and another for executing actions in the browser. This server runs on macOS with Python 3.12 and Google Chrome, making it ideal for users who want to give Claude the ability to navigate websites, fill forms, and interact with web content directly from conversations.
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 2026-09-02.
Scan details: Circle-IR · 2026-09-02 · 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/ashley-ha/mcp-manus
- Author type
- human
- Last scanned
- 2026-09-02
- Updated
- 2026-09-02
Use via MCP
Resolve Browser Automation 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.