MCP Server Tauri

Community

Give your AI assistant superpowers for Tauri development

How to install ↓ Compare GitHub source repository ↗

Category: Dev Tools #199 of 438
Stars: ★ 317 Popular
Transport: stdio (local process)
Runtime: Node.js 20+ · Rust
Credentials: No credential needed
License: MIT
Last commit: 2 days ago
Tools: 20

54FMRS · D

This server provides comprehensive MCP integration for Tauri v2 development, with rich UI automation tools, IPC monitoring, and log reading. It suits Tauri developers needing AI-assisted debugging and testing. However, since the project declares potential bugs, use with caution.

Strongest · Documentation 14/20 Weakest · Reliability 7/20

Reliability

7/20

Security and permissions

8/20

Maintenance

13/20

Documentation

14/20

Setup experience

12/20

Why each score

Reliability 7/20: The manifest and README describe a coherent stdio server exposing 21 tools across UI automation, IPC, logs and mobile with a plausible npm install path. However, the supplied material contains no CI workflow, no committed tests, and no verifiable MCP handshake evidence, so per static calibration reliability cannot exceed 12. The server depends on an external bridge plugin and a WebSocket session on port 9223; failures such as a missing plugin, port conflicts, or the app not running are likely yet their handling is undocumented, and the README itself carries an 'agentic coding' bug disclaimer. Deductions applied; score 7.
Security and permissions 8/20: No red-line issues (credential theft, covert exfiltration, or destructive defaults) are evident. The server exposes powerful, potentially destructive tools — webview_execute_js, ipc_execute_command, manage_window — and its security boundary rests on a local WebSocket on port 9223 whose binding scope and authentication are never disclosed in the supplied material. The README says the assistant asks permission before modifying project files, which is a partial confirmation mechanism, but there is no documented least-privilege model and no per-operation confirmation or scoping for dangerous actions. Score 8.
Maintenance 13/20: The repository is not archived, uses an explicit MIT license with a named maintainer, and both npm and crates.io packages appear published, with release scripts present in the repo. But the evidence also shows 22 open issues with no visible issue-response policy, dependency-update cadence, or security-response channel, so sustained governance cannot be fully verified. Score 13.
Documentation 14/20: The README is layered and comprehensive: quick start, prerequisites, concrete aix configuration commands for many clients, tables for all 21 tools, slash-command workflows, an architecture diagram, and development/release instructions, plus links to a VitePress site, plugin README and specs. Deductions: no security or authentication notes, no troubleshooting/FAQ section in the supplied material, tool parameters are only summarized rather than fully specified, and the depth of the linked API reference cannot be verified from the provided files. Score 14.
Setup experience 12/20: The install path is clearly spelled out: prepare Node 20+, Rust and the Tauri CLI, add the server to many AI clients with a one-line aix command, restart, then install the MCP Bridge plugin into the Tauri app with assistant guidance; a CLI mode with explicit commands is also documented. However, setup is multi-component and depends on an external WebSocket session plus a plugin injected into the user's app, with only a manual fallback link; no committed CI or end-to-end tests were supplied to prove the path, so per static calibration setup cannot exceed 15. Score 12.

Static review · not runListed 2026-08-07

Read the FMRS scoring method →

Fit and risk

What it can accessRuns commands or codeUses the networkControls a browser

Best for

Developers using Tauri v2
Those wanting AI assistance in building, testing, and debugging Tauri apps
Teams needing UI automation testing in Tauri applications

Not for

Non-Tauri v2 projects
Scenarios requiring headless browser automation (like Selenium or Playwright)
General web automation unrelated to Tauri development

Required permissions

Requires access to running Tauri app (via WebSocket port 9223)
May need system command execution permissions (e.g., launching simulators)
Requires write access to project files for plugin configuration

Risks and side effects

Tools may contain bugs (project states developed with agentic coding tools)
Executing arbitrary IPC commands could cause unexpected behavior or data modification
Automation features may affect app state, use with caution
External dependencies (like Xcode, Android SDK) may need additional setup

Setup

Before you start

Runtime：Node.js 20+ · Rust

Ensure Node.js 20+, npm, Rust, Cargo, and Tauri CLI (npm install -g @tauri-apps/cli@next) are installed.
Use npx -y @a1st/aix add mcp tauri --command 'npx @hypothesi/tauri-mcp-server' --user to add the server to your AI assistant (supports Claude Code, Cursor, Windsurf, etc.).
Restart your AI assistant.
Ask the AI to set up the MCP Bridge plugin in your Tauri app (or manually configure).

.cursor/mcp.json

{
  "mcpServers": {
    "tauri": {
      "command": "npx",
      "args": [
        "@hypothesi/tauri-mcp-server"
      ]
    }
  }
}

Shown for Cursor. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.

.vscode/mcp.json

{
  "servers": {
    "tauri": {
      "command": "npx",
      "args": [
        "@hypothesi/tauri-mcp-server"
      ]
    }
  }
}

Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).

Terminal

claude mcp add tauri -- npx @hypothesi/tauri-mcp-server

Run it in a terminal; replace any <…> placeholders with your own values first.

Generate and validate client config

Check that it works

The client's tool list should show 21 tools such as get_setup_instructions, webview_screenshot, and ipc_monitor; alternatively ask the AI to "Help me set up the Tauri MCP Bridge plugin" — a returned setup guide confirms the connection.

Troubleshooting

Ensure Tauri app has MCP Bridge plugin enabled and running.
Check WebSocket port 9223 is accessible and not blocked by firewall.
Verify Node.js version >=20 and Tauri CLI is properly installed.
Restart AI assistant to load new MCP configuration.
See documentation: https://hypothesi.github.io/mcp-server-tauri

Things to try

Once connected, you can ask your AI assistant things like:

Help me set up the Tauri MCP Bridge plugin in my Tauri v2 project
Take a screenshot of my app and read the console logs to find JavaScript errors
Click the login button, then wait for the dashboard element to appear
List my Android devices and iOS simulators

Tools 20

get_setup_instructions read-only

Get setup/update instructions for the MCP Bridge plugin.

driver_session writes

Start/stop/status automation session.

webview_find_element read-only

Find elements by selector.

read_logs read-only

Read console, Android, iOS, or system logs.

webview_interact writes

Click, scroll, swipe, focus, long-press.

webview_screenshot read-only

Capture webview screenshots.

webview_keyboard writes

Type text or send key events.

webview_wait_for read-only

Wait for elements, text, or events.

Show 12 more tools

webview_get_styles read-only

Get computed CSS styles.

webview_execute_js writes

Execute JavaScript in webview.

webview_dom_snapshot read-only

Get structured accessibility tree snapshot.

webview_select_element read-only

Visual element picker — user clicks an element, returns metadata + screenshot.

webview_get_pointed_element read-only

Get metadata for element user Alt+Shift+Clicked.

manage_window writes

List windows, get info, or resize.

ipc_execute_command writes

Execute Tauri IPC commands.

ipc_get_backend_state read-only

Get app metadata and state.

ipc_monitor writes

Start/stop IPC monitoring.

ipc_get_captured read-only

Get captured IPC traffic.

ipc_emit_event writes

Emit custom events.

list_devices read-only

List Android devices and iOS simulators.

Use cases

Perform UI automation on Tauri apps, such as screenshots, clicks, and typing.

Monitor and inspect Tauri IPC calls for debugging.

Access and analyze logs from the app (console, Android, iOS).

List available mobile simulators/devices for development testing.

Supported clients

Claude

Cursor

Windsurf

VS Code

Cline

Roo Cline

Zed

Goose

Warp

Codex

Listed from the project's documentation, not tested by this site.

Overview

A Model Context Protocol (MCP) server and plugin for Tauri v2 development. It enables AI assistants like Claude, Cursor, and Windsurf to build, test, and debug Tauri v2 applications by providing screenshots, DOM state, console logs, and tools to interact with the app.

Similar servers

Context7 80 · B

Upstash's official server providing up-to-date third-party library docs for AI coding assistants

★ 62.9k · Tools 2 Compare with this →

NPM Sentinel MCP Server 79 · B

AI-powered NPM package analysis MCP server

★ 18 · Tools 19 Compare with this →

MartinLoop MCP Server 79 · B

An independent control layer that gives AI coding agents budgets, brakes, and receipts

★ 410 Compare with this →

GitHub MCP Server 76 · B

GitHub's official MCP server for managing repos, issues, PRs, and workflows via natural language

★ 33.5k · Tools 15 Compare with this →

Compare with other MCP servers

Source revision 216ef221bcf9 Data synced 2026-10-12 Read the FMRS scoring method