A local MCP server that replays recorded website maps instead of exploring browser routes again. MCP is a standard way for an AI agent to call external tools.

Use it when an agent needs to access or replay recorded website navigation through the webnav tool.

It can reuse previously recorded navigation paths, reducing repeated exploration of the same website. The description does not specify the available commands.

webnav — MCP server for Claude Code and Codex by lucyfuur94

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/lucyfuur94/webnav-core

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/mcp/lucyfuur94/webnav-core/webnav.svg)](https://agentmods.dev/mcp/lucyfuur94/webnav-core/webnav)

Your own site

<a href="https://agentmods.dev/mcp/lucyfuur94/webnav-core/webnav"><img src="https://agentmods.dev/badge/mcp/lucyfuur94/webnav-core/webnav.svg" alt="Measured on agentmods" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

webnav scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

server.json · 10 lines

What it actually says

{
  "webnav": {
    "command": "npx",
    "args": [
      "-y",
      "@dikshanty94/webnav"
    ],
    "env": {}
  }
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

7d ago First seen · 10 lines scan A 9aed5152e126

Subscribe to this mod's changes

webnav is an MCP server published in the GitHub repository lucyfuur94/webnav-core (0 stars, last pushed 1mo ago), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Browser automation agent-tools ai-agents browser-automation llm-tools playwright

drisp-browser-dev

MCP server "drisp-browser-dev" as configured in drisplabs/browser-mcp. Runs dist/src/index.js with node.

drisplabs/browser-mcp · not measured

tap

Browser MCP for logged-in tasks. Uses your Chrome — credentials stay local. Zero-token replay. Runs locally from the @taprun/cli npm package.

LeonTing1010/tap · not measured

crawlio-browser

Bridge a live Chrome browser to your agent: 150 tools for capture, extraction, and observation. Runs locally from the crawlio-browser npm package.

Crawlio-app/crawlio-browser · not measured

footnote-mcp

MCP server for source-grounded web research: search, structured-data extraction, evidence verification, and browser automation. Runs locally from the footnote-mcp Python package.

KazKozDev/footnote-mcp · not measured

fortress

Open stealth-browser framework — drive a real recompiled-Chromium (Fortress) that defeats bot-detection fingerprint suites. Drop-in stealth for browser-use, Playwright, Crawl4AI, with an MCP server for AI agents. Runs locally from the tilion Python package. Needs 5 environment variables to run.

tiliondev/fortress · not measured

camoufox-playwright-mcp

The Playwright MCP, on Camoufox. Same tools, harder-to-detect browser. Runs locally from the camoufox-playwright-mcp Python package.

chandu-cpz/camoufox-playwright-mcp · not measured