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.
git clone --depth 1 https://github.com/hypothesi/mcp-server-tauriWrote 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.
[](https://agentmods.dev/plugins/hypothesi/mcp-server-tauri/cli)<a href="https://agentmods.dev/plugins/hypothesi/mcp-server-tauri/cli"><img src="https://agentmods.dev/badge/plugins/hypothesi/mcp-server-tauri/cli/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/hypothesi/mcp-server-tauri/cli"><img src="https://agentmods.dev/badge/plugins/hypothesi/mcp-server-tauri/cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
tauri-mcp-cli 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 8d 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.
What it actually says
{
"name": "tauri-mcp-cli",
"description": "Exposes Tauri MCP skills that can be used to control the webview of a running Tauri app from an AI assistant.",
"version": "0.13.1",
"author": {
"name": "hypothesi"
},
"license": "MIT",
"homepage": "https://github.com/hypothesi/mcp-server-tauri",
"repository": "https://github.com/hypothesi/mcp-server-tauri"
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 57 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 8d ago Changed f35f05e33aa3
- 1mo ago First seen · 12 lines scan A 41fb8197a3b0
tauri-mcp-cli is a plugin published in the GitHub repository hypothesi/mcp-server-tauri (323 stars, last pushed 4d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.
Other plugins, from other repositories
vibesurfer
Agent-native headless browser.
only-cli
Browse websites from the terminal in a few hundred tokens.
assay
Opens a page you changed, drives every control it offers, and reports what it did and what happened. One line every time, clean or not.
string
Use String apps and the web through one MCP tool. Install an app from a GitHub URL, read pages as markdown, run typed actions on documents — the whole String runtime exposed as a single mcpstringstring tool, with a skill that teaches Claude when and how to use it.
browser-relay
Let agents use the Chrome you already have open and logged in through a Skill + CLI, locally or across machines.
cc-arsenal-skills
Specialty skills: Browser automation (agent-browser), turning docs sites, PDFs, folders and YouTube videos into grounded agent skills (anything-to-skill), third-party skill discovery (find-skills), specification-driven skill creation with eval system and description optimization (create-skill v2.0), CLAUDE.md rule…