tap

tap is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from LeonTing1010/tap. Its token cost is not measured, scanned A, original, MIT.

A local browser connection for tasks that require your already signed-in Chrome session. It runs from an npm command, so login details remain on your computer.

In plain words
What is it for?
Running coding-agent tasks in websites where you are already signed in, using Chrome through a local command.
Why use it?
It avoids asking you to copy credentials into the agent or repeat browser actions using tokens. It is intended for tasks where access depends on your existing browser login.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it.

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.

agentmods
npx agentmods add mcp/leonting1010/tap/mcp-tap
Clone the repo
git clone --depth 1 https://github.com/LeonTing1010/tap

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.

agentmods badge for tap

README.md
[![agentmods](https://agentmods.dev/badge/mcp/leonting1010/tap/mcp-tap.svg)](https://agentmods.dev/mcp/leonting1010/tap/mcp-tap)
Your own site
<a href="https://agentmods.dev/mcp/leonting1010/tap/mcp-tap"><img src="https://agentmods.dev/badge/mcp/leonting1010/tap/mcp-tap.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. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

tap 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 6d 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.

docs/.well-known/mcp/server.json · 12 lines

What it actually says

{
  "tap": {
    "command": "npx",
    "args": [
      "-y",
      "@taprun/cli",
      "mcp",
      "stdio"
    ],
    "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.

  1. 6d ago First seen · 12 lines scan A b19cf9148a7c

Subscribe to this mod's changes

tap is an MCP server published in the GitHub repository LeonTing1010/tap (17 stars, last pushed 27d ago), licensed MIT. 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 2026-08-30.