Selenium WebDriver
Selenium WebDriver MCP server by V S Pasham that enables AI assistants to control web browsers programmatically through Selenium WebDriver. Built with TypeScript and supporting Chrome, Firefox, and Edge browsers, it provides comprehensive browser automation tools including navigation, element interaction (clicking, typing, hovering), form handling, screenshot capture, JavaScript execution, and advanced actions like drag-and-drop and dropdown selection. The implementation uses a service-oriented architecture with separate modules for browser management, element operations, and user actions, while maintaining session state through a centralized StateManager. Designed for automated testing workflows, web scraping tasks, and AI-driven browser automation where agents need to interact with web applications as if they were human users.
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 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · 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/pshivapr/selenium-mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Selenium WebDriver 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.