jevnav is a browser layer for agents and tests. It reads a page as facts (structure, computed styles, the controls on screen), lets Jev — TypeSafe's model for structured questions — pick the element…
jevnav is an MCP project maintained in the dtduc-git/jevnav repository. The maintainer describes its purpose as “jevnav is a browser layer for agents and tests. It reads a page as facts (structure, computed styles, the controls on screen), lets Jev —…”. Read the project documentation for the complete scope.
The documented pypi package is jevnav. The configuration below comes from the maintainer’s example; adapt its paths and account values to your environment.
The example declares TYPESAFE_API_KEY. Secret-looking values have been replaced with placeholders. Required and optional labels are shown only when the documentation states them.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
{
"mcpServers": {
"jevnav": {
"command": "uvx",
"args": [
"jevnav",
"mcp"
],
"env": {
"TYPESAFE_API_KEY": "YOUR_TYPESAFE_API_KEY"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| TYPESAFE_API_KEY | Declared in the maintainer’s client configuration. | Check documentation |
Use Microsoft’s Playwright MCP server to navigate pages, inspect accessibility snapshots, fill forms and capture browser screenshots.
The original Chromium automation reference server — simple, screenshot-driven browser control.
MCP server for Next AI Draw.io - AI-powered diagram generation with real-time browser preview
Ask-Me MCP - Human-in-the-Loop Model Context Protocol Server
A Model Context Protocol (MCP) server that provides comprehensive access to SendGrid's API v3 for email marketing, transactional email operations, dynamic template management, and detailed analytics. Features 154 tools…
Play DOOM via MCP - works with Claude Code, Cursor, and any MCP client