Selenium Mcp

io.github.gaforovPublished by GitHub account gaforovv0.3.0Updated Oct 24, 2026

Selenium MCP server for AI agents — 41 browser automation tools with snapshots and sessions.

VerifiedSTDIODesktop onlyBrowser Automation Developer Tools

Server details

Identifier: io.github.gaforov/selenium-mcp
Transport: STDIO
Runtime: Desktop only
Trust: Verified
Published: Sep 16, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified the GitHub account gaforov for this listing. That does not show the account is the product's maker.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.gaforov%2Fselenium-mcp.svg)](https://sourceweft.com/mcp/io.github.gaforov%2Fselenium-mcp?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

Selenium-based MCP server giving an AI assistant 41 tools to drive a real Chrome, Firefox or Edge browser locally, with page snapshots and multi-session…

What you can do: Start, stop and manage parallel browser sessions, and navigate with history, redirect waits and URL/title reads.
Find and wait for elements, capture page snapshots with stable element refs, and read page source.
Click, retry clicks, hover, type, select options, scroll, press keys and upload files.
Read text and attributes, run assertions, execute scripts and run batched multi-step sequences.
Save, list and delete per-domain selector hints, manage windows, frames, alerts and cookies, and take screenshots.
When to use it: Useful when an assistant should operate a real browser on the user's machine: end-to-end web testing, filling in forms, checking rendered pages, responsive viewport checks, or repeatable automations that benefit from saved selector hints.
Requirements: Runs as a local stdio process, typically via npx from the npm package. Needs Node.js 20+ and Chrome, Firefox or Edge installed; Selenium Manager provisions the matching driver automatically. Optional tracing is enabled with the SELENIUM_MCP_TRACE and SELENIUM_MCP_TRACE_PATH environment variables.

Before you install

The assistant can click, type, upload files, run scripts and change cookies in a real browser, so actions affect live sites and accounts. Optional tracing writes an NDJSON log of every tool call to disk, which may capture sensitive page and input details. Desktop-only; no authentication is declared.

Installation

In SourceWeft

Open Selenium Mcp in the dashboard and add it to a workspace.
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

selenium-mcp

Selenium MCP server for AI agents — 41 tools for real-browser automation: navigation, clicking, typing, assertions, screenshots, multi-session management, page snapshots with stable element refs, persistent selector hints, and batched multi-step execution.

[npm version] [npm downloads] [CI] [license] [node]

Built with TypeScript, the official MCP SDK, and Selenium WebDriver — strict zod input validation, explicit waits, and structured responses designed for LLM agents.

One-Click Install

[Install in Cursor] [Install in VS Code] [Install in VS Code Insiders]

What's new in 0.3.0

New tools: select_option for dropdowns, scroll (including infinite-scroll pages and scrollable panels), history for back, forward, and refresh, and wait_for_page to wait for a URL or title after a redirect.
Responsive testing: window can now resize the viewport to an exact size, such as a 390x844 phone, or maximize it.
Better tool choice by AI agents: every tool and parameter now explains what it does, what it returns, and when to use a similar tool instead.
Breaking: open_url and wait_until_visible were removed as duplicates. Use navigate, and wait_for_element with visible: true.
Verified releases: every release is tested end to end against a real browser and published with npm provenance.

See the changelog for details.

Setup

Claude Code

Claude Desktop / Cursor / Windsurf / other MCP clients

Add to your client's MCP config (e.g. claude_desktop_config.json or .cursor/mcp.json):

json

{  "mcpServers": {    "selenium": {      "command": "npx",      "args": ["-y", "@gaforov/selenium-mcp@latest"]    }  }}

{  "mcpServers": {    "selenium": {      "command": "npx",      "args": ["-y", "@gaforov/selenium-mcp@latest"]    }  }}

VS Code

Goose

IntelliJ IDEA / JetBrains IDEs

Settings → Tools → AI Assistant → Model Context Protocol → Add, with command npx and arguments -y @gaforov/selenium-mcp@latest. Full walkthrough in docs/CLIENT_INTEGRATION.md.

From source

Then point your MCP client at node /absolute/path/to/selenium-mcp/dist/server.js.

Example Usage

Ask your AI agent:

Use selenium-mcp to open Chrome, go to https://example.com, read the page title, take a screenshot, and close the browser.

The agent chains start_browser → navigate → get_title → take_screenshot → stop_browser on its own — no scripting needed.

Requirements

Node.js 20+
Chrome, Firefox, or Edge installed (Selenium Manager provisions the matching driver automatically)

How it compares

Most Selenium MCP servers wrap WebDriver's basic commands. This one adds the layer that makes agents reliable:

Capability	selenium-mcp	Typical Selenium MCP servers
Page snapshot with stable element refs (`capture_page`)	✅	rare
Persistent per-domain selector memory (`selector_hint_*`)	✅	❌
Parallel multi-session browsing	✅	rare
Batched multi-step execution in one call	✅	❌
Built-in test assertions	✅	some
Tool-call tracing (NDJSON audit log)	✅	❌
Strict input validation + structured errors	✅	varies
Every tool and parameter described for AI agents (enforced by tests)	✅	varies
End-to-end tests against a real browser in CI	✅	some

Why selenium-mcp

Snapshot-first workflows — capture_page returns a page snapshot with stable element refs the agent can act on directly, no brittle selector guessing
Selector hints — persist working locators per domain so repeat automations get faster and more reliable over time
Batched execution — batch_execute runs constrained multi-step sequences in a single tool call, cutting round-trips
Multi-session — create, select, list, and destroy parallel browser sessions
Agent-friendly errors — every response is structured and validated with zod, so agents can recover instead of stalling
Optional tracing — NDJSON trace of every tool call for debugging and auditing

Tools (41)

Category	Tools
Browser lifecycle	`start_browser`, `stop_browser`, `session_create`, `session_select`, `session_list`, `session_destroy`
Navigation	`navigate`, `history` (back/forward/refresh), `wait_for_page` (URL/title), `get_current_url`, `get_title`
Element discovery	`find_element`, `wait_for_element`, `capture_page`, `get_page_source`
Interaction	`click`, `retry_click`, `interact` (hover/double/right-click), `type`, `select_option`, `scroll`, `press_key`, `upload_file`
Reading	`get_text`, `get_attribute`
Assertions	`assert_text`, `assert_visible`, `assert_attribute`
Scripting	`execute_script`, `batch_execute`
Selector hints	`selector_hint_save`, `selector_hint_get`, `selector_hint_list`, `selector_hint_delete`
Windows & context	`window` (tabs, windows, resize/maximize), `frame`, `alert`
Cookies	`add_cookie`, `get_cookies`, `delete_cookie`
Capture	`take_screenshot`

Full parameter documentation: docs/TOOL_REFERENCE.md

MCP Resources

browser-status://current — live browser/session status
accessibility://current — accessibility snapshot of the current page

Optional Tracing

Enable lightweight NDJSON tracing of all tool calls:

If SELENIUM_MCP_TRACE_PATH is omitted, the default is logs/selenium-mcp-trace.ndjson.

Documentation

Contributing

Contributions are welcome — bug reports, feature requests, and pull requests. See CONTRIBUTING.md to get started.

License

MIT. See LICENSE.

Source: README.md at commit d04777a

Tools

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

Version history

v0.3.0LatestSep 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