Selenix MCP Server

io.github.markmirceaPublished by GitHub account markmirceav1.0.7Updated Oct 24, 2026

MCP server that bridges local apps with Selenix for browser automation.

VerifiedSTDIODesktop onlyBrowser AutomationDeveloper Tools

Overview

AI-generated overview

Bridges Claude Desktop to the Selenix desktop app so an assistant can create, run, debug, and manage browser automation tests.

What you can do
The server translates assistant tool calls into HTTP requests to a bridge running inside the Selenix desktop app. Read tools cover screenshots, annotated page HTML, regex HTML search, test and command listings, step results, logs, and workspace context. Write tools add, replace, or fix commands in a test, and run_test executes a test and waits up to two minutes for results.
When to use it
Use it when you already work in Selenix and want an assistant to inspect, author, or repair browser automation tests through chat instead of the built-in AI Assistant. It is desktop-only and not useful without the Selenix app running.
Requirements
Selenix desktop app installed with the MCP Server bridge enabled in System Settings, Claude Desktop, and Node.js 18 or later. Install via npm package @selenix/mcp-server, the bundled copy inside Selenix, or a manually downloaded bundle, then point the Claude Desktop config at the file. The bridge listens only on 127.0.0.1 and uses a bearer token generated at Selenix startup; connection details are read from ~/.selenix/bridge.json.
Before you install
The bridge has full access to Selenix internals, equivalent to the built-in AI Assistant, so write tools can change or replace test commands and run_test executes tests in a real browser. The manifest declares a secret environment variable named YOUR_API_KEY, but the README does not explain what it is for; treat it as a credential and do not share it. Editing the Claude Desktop config file can break the app if the JSON is malformed.

Installation

In SourceWeft

  1. Open Selenix MCP Server in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Selenix MCP Server

[npm version]

Connect Claude Desktop to Selenix via the Model Context Protocol. Chat with Claude to create, run, debug, and manage browser automation tests — just like using the built-in AI Assistant, but powered by Claude.

[Selenix-MCP MCP server]

Prerequisites

Enable the Bridge in Selenix

Before using any setup method below, enable the bridge inside Selenix:

  1. Open Selenix
  2. Go to System Settings (gear icon in the sidebar)
  3. Scroll to the MCP Server section
  4. Set Enable MCP Server to Yes

This starts a local bridge server that the MCP server connects to.

Setup

Choose one of the following methods:

Option A: Install via npm (recommended)

bash
npm install -g @selenix/mcp-server

Then find your global npm path:

bash
npm root -g

Open your Claude Desktop config file:

  • Windows: Press Win+R, paste %APPDATA%\Claude\claude_desktop_config.json, press Enter
  • macOS: Open ~/Library/Application Support/Claude/claude_desktop_config.json

Add the Selenix MCP server, replacing the path with the output from npm root -g:

json
{  "mcpServers": {    "selenix": {      "command": "node",      "args": ["<npm-root-path>/@selenix/mcp-server/dist/bundle.js"]    }  }}

Example (Windows with nvm):

json
{  "mcpServers": {    "selenix": {      "command": "node",      "args": ["C:/Users/YourName/AppData/Local/nvm/v18.20.8/node_modules/@selenix/mcp-server/dist/bundle.js"]    }  }}

Example (macOS/Linux):

json
{  "mcpServers": {    "selenix": {      "command": "node",      "args": ["/usr/local/lib/node_modules/@selenix/mcp-server/dist/bundle.js"]    }  }}

If you already have other MCP servers configured, add "selenix" alongside them inside the existing "mcpServers" object.

Option B: Use the bundled version (no npm required)

If you installed Selenix as a desktop app, the MCP server is already bundled. No need to install anything — just point Claude Desktop to the bundled file.

Find your Selenix install folder and look for resources/mcp-server/index.js, then add to your Claude Desktop config:

json
{  "mcpServers": {    "selenix": {      "command": "node",      "args": ["C:/path/to/Selenix/resources/mcp-server/index.js"]    }  }}

Typical Windows path:

C:/Users/YourName/AppData/Local/Programs/Selenix/resources/mcp-server/index.js

Option C: Manual download

  1. Download bundle.js from the npm package page or from the releases page
  2. Save it somewhere on your machine (e.g., C:/selenix-mcp/bundle.js)
  3. Add to your Claude Desktop config:
json
{  "mcpServers": {    "selenix": {      "command": "node",      "args": ["C:/selenix-mcp/bundle.js"]    }  }}

Node.js is still required — the MCP server is a single JavaScript file with no other dependencies.

Verify

Restart Claude Desktop after editing the config. You should see the Selenix tools icon (hammer) in the chat input area.

Try asking Claude:

  • "What tests are in my Selenix project?"
  • "Create a test that opens google.com and searches for 'selenium automation'"
  • "Run the current test and fix any failures"
  • "Take a screenshot of the browser"

How It Works

Claude Desktop <--stdio--> MCP Server <--HTTP--> Bridge Server (inside Selenix)

The MCP server translates Claude's tool calls into HTTP requests to a bridge server running inside Selenix. The bridge has full access to Selenix internals — the same capabilities as the built-in AI Assistant.

  • The bridge only listens on 127.0.0.1 (localhost) — no network exposure
  • Auth is handled via a bearer token auto-generated each time Selenix starts
  • Connection config is stored at ~/.selenix/bridge.json and re-read on every call, so restarting Selenix does not require restarting Claude Desktop

Available Tools

Reading & Inspection

ToolDescription
get_screenshotCapture a screenshot of the browser window
get_page_htmlGet the page HTML with interactive elements annotated
get_search_htmlSearch page HTML by regex pattern
get_selected_command_infoGet DOM context for a command's target element
get_current_testGet all commands in the current test
get_test_listList all tests in the project
get_test_by_nameGet a test by its name
get_command_listList all available Selenix commands
get_command_infoGet detailed docs for a specific command
get_project_infoGet project metadata
get_active_suiteGet the active test suite
get_step_resultsGet pass/fail results from the last test run
get_logsGet recent logs (all types), 20 per page, most recent first. Optional page param for pagination.
get_workspace_contextGet a summary of the current workspace

Writing & Execution

ToolDescription
add_commandsAdd commands to a test at a specific position
run_testRun a test and wait for results (up to 2 minutes)
clear_and_replace_commandsReplace all commands in a test
fix_commandsApply targeted fixes — update, remove, or insert commands

Troubleshooting

"Cannot read Selenix bridge config" Selenix isn't running or the MCP Server isn't enabled. Open Selenix → System Settings → set Enable MCP Server to Yes.

"Cannot connect to Selenix bridge" Selenix may have just restarted. Try the request again — the MCP server will automatically pick up the new connection details.

Tools not appearing in Claude Desktop Make sure you restarted Claude Desktop after editing the config file. Verify the config JSON is valid (no trailing commas, correct brackets).

Claude Desktop won't open after config change The config JSON is likely malformed. Open the config file in a text editor, fix the JSON syntax, and try again. Common issues: missing comma between entries, trailing comma after the last entry.

Uninstall

bash
npm uninstall -g @selenix/mcp-server

Then remove the "selenix" entry from your Claude Desktop config file and restart Claude Desktop.

Source: README.md at commit 14d0385

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.7LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts