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.
npx agentmods add skills/hypothesi/mcp-server-tauri/tauri-mcp-clinpx skills add hypothesi/mcp-server-tauri --skill tauri-mcp-cligit 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/skills/hypothesi/mcp-server-tauri/tauri-mcp-cli)<a href="https://agentmods.dev/skills/hypothesi/mcp-server-tauri/tauri-mcp-cli"><img src="https://agentmods.dev/badge/skills/hypothesi/mcp-server-tauri/tauri-mcp-cli.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00057 | $0.01589 |
| Opus 5 | $0.00028 | $0.00794 |
| Sonnet 5 | $0.00011 | $0.00318 |
| Haiku 4.5 | $0.00006 | $0.00159 |
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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- tauri-mcp-cli — 92% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tauri MCP CLI
Use this skill for the entire CLI workflow. The package intentionally ships a single bundled skill so agents do not need to pick between overlapping domain-specific skills.
Prerequisites
- The app is running in development mode, usually with
cargo tauri dev. - The
tauri-plugin-mcp-bridgeplugin is installed and registered. src-tauri/tauri.conf.jsonsetswithGlobalTauri: true.
Core Rule
Start or verify a driver session before calling almost any other tool:
tauri-mcp driver-session start --port 9223
tauri-mcp driver-session status --json
driver-session start can succeed even when no app is reachable, so always check connected: true in the status output.
Session and Daemon Lifecycle
# Start a session
tauri-mcp driver-session start --port 9223
# Run one or more commands in separate shell invocations
tauri-mcp webview-screenshot --file before.png
tauri-mcp webview-interact --action click --selector "#submit-btn"
tauri-mcp webview-screenshot --file after.png
# End the session
tauri-mcp driver-session stop
The CLI uses MCPorter keep-alive mode, so the background daemon preserves session state across separate tauri-mcp ... commands.
Use daemon commands only when the background process itself is unhealthy:
tauri-mcp daemon status
tauri-mcp daemon restart
tauri-mcp driver-session start --port 9223
UI Interaction
# Click or focus an element
tauri-mcp webview-interact --action click --selector "#submit-btn"
tauri-mcp webview-interact --action focus --selector "#search"
# Type into a field
tauri-mcp webview-keyboard --action type --selector "#email" --text "[email protected]"
# Wait before interacting with async UI
tauri-mcp webview-wait-for --type selector --value "#success-msg" --timeout 5000
tauri-mcp webview-interact --action click --selector "#success-msg"
# Keyboard shortcuts and scrolling
tauri-mcp webview-keyboard --action press --key "s" --modifiers '["Control"]'
tauri-mcp webview-interact --action scroll --selector ".content" --scroll-y 300
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.
- 6d ago First seen · 214 lines · 57 tokens per session scan A 65453a3eccf2
tauri-mcp-cli is a skill published in the GitHub repository hypothesi/mcp-server-tauri (297 stars, last pushed 8d ago), licensed MIT. It adds 57 tokens to every session and 1,589 once invoked, about $0.0003 per session on Opus 5. 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 skills, from other repositories
broken-link-checker
Scans a website to find broken links (404s, 500s). Crawls internal pages, identifies broken outbound links, and reports source pages for easy fixing. Use this when the user asks to "check for broken links", "find 404s", "audit my links", or "is my site healthy".
anti-detect-browser
Drive Chromium from standard Playwright APIs with a real-device fingerprint applied in the kernel, one persistent isolated profile per identity, and a per-profile proxy whose exit IP sets timezone and WebRTC - JavaScript (npm 'anti-detect-browser') or Python (PyPI 'antibrow'). Use when sessions must stay logged in…
browser-mcp-agent
Give an AI agent its own real browser over MCP tool calls - launch, navigate, click, fill, screenshot, extract text, run JS - with a kernel-level real-device fingerprint and a persistent profile, so the session stays logged in between runs and pages see one coherent device instead of a headless build. No Playwright or…
multi-account-isolation
Verify that browser profiles are actually isolated from one another instead of assuming it - confirm each profile's timezone agrees with its own exit IP, that WebRTC exposes only the proxy, that canvas and WebGL hashes stay identical across relaunches of one profile, and that no two profiles share a persona, a cookie…
vibesurfer
Agent-native headless browser. 26 primitives over a Unix-socket wire protocol. Real WKWebView (macOS), WebKitGTK 6 (Linux), or WebView2 (Windows) — all three engines verified per-commit by a real-browser integration suite. Optimistic concurrency via state tokens; tree-delta wire format; durable session/page/auth state…
tauri-pilot
Inspect, interact with, and test a running Tauri v2 app via CLI. Communicates over Unix socket using JSON-RPC 2.0. Use when testing UI, automating interactions, or debugging a Tauri app.