YetiBrowser
YetiBrowser MCP provides AI assistants with direct browser control through a companion Chrome/Firefox extension and WebSocket bridge, enabling real-time web automation without requiring separate browser instances. Built by YetiDevWorks using TypeScript and the Model Context Protocol SDK, it offers 13 tools including DOM snapshots with accessibility data, form interactions, navigation controls, screenshot capture, and console log access, all operating on the user's actual browser tab rather than a headless environment. The implementation features automatic port discovery to avoid conflicts with multiple MCP instances, supports both Chrome and Firefox through shared extension code, and maintains local-only operation with no external data transmission, making it valuable for web testing workflows, form automation, content extraction, and building AI assistants that need to interact with live web applications in the user's existing browser session.
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 2026-09-01.
Scan details: Circle-IR · 2026-09-01 · 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/yetidevworks/yetibrowser-mcp
- Author type
- human
- Last scanned
- 2026-09-01
- Updated
- 2026-09-01
Use via MCP
Resolve YetiBrowser 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.