Skip to content
Back to search

mcp-selenium

An MCP implementation for Selenium WebDriver

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/angiejones--mcp-selenium/badge.svg)](/listings/angiejones--mcp-selenium)

HTML

<a href="/listings/angiejones--mcp-selenium"><img src="/api/listings/angiejones--mcp-selenium/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

<details open> <summary><strong>Goose (Desktop)</strong></summary>

Paste into your browser address bar:

goose://extension?cmd=npx&arg=-y&arg=%40angiejones%2Fmcp-selenium%40latest&id=selenium-mcp&name=Selenium%20MCP&description=automates%20browser%20interactions

</details>

<details> <summary><strong>Goose (CLI)</strong></summary>

goose session --with-extension "npx -y @angiejones/mcp-selenium@latest"

</details>

<details> <summary><strong>Claude Code</strong></summary>

claude mcp add selenium -- npx -y @angiejones/mcp-selenium@latest

</details>

<details> <summary><strong>Cursor / Windsurf / other MCP clients</strong></summary>

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

</details>

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 288 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # MCP Selenium Server
  2. A Model Context Protocol (MCP) server for Selenium WebDriver — browser automation for AI agents.
  3. [![Watch the video](https://img.youtube.com/vi/mRV0N8hcgYA/sddefault.jpg)](https://youtu.be/mRV0N8hcgYA)
  4. <a href="https://glama.ai/mcp/servers/@angiejones/mcp-selenium">
  5. <img width="380" height="200" src="https://glama.ai/mcp/servers/@angiejones/mcp-selenium/badge" alt="Selenium MCP server" />
  6. </a>
  7. ## Setup
  8. <details open>
  9. <summary><strong>Goose (Desktop)</strong></summary>
  10. Paste into your browser address bar:
  11. ```
  12. goose://extension?cmd=npx&arg=-y&arg=%40angiejones%2Fmcp-selenium%40latest&id=selenium-mcp&name=Selenium%20MCP&description=automates%20browser%20interactions
  13. ```
  14. </details>
  15. <details>
  16. <summary><strong>Goose (CLI)</strong></summary>
  17. ```bash
  18. goose session --with-extension "npx -y @angiejones/mcp-selenium@latest"
  19. ```
  20. </details>
  21. <details>
  22. <summary><strong>Claude Code</strong></summary>
  23. ```bash
  24. claude mcp add selenium -- npx -y @angiejones/mcp-selenium@latest
  25. ```
  26. </details>
  27. <details>
  28. <summary><strong>Cursor / Windsurf / other MCP clients</strong></summary>
  29. ```json
  30. {
  31. "mcpServers": {
  32. "selenium": {
  33. "command": "npx",
  34. "args": ["-y", "@angiejones/mcp-selenium@latest"]
  35. }
  36. }
  37. }
  38. ```
  39. </details>
  40. ## Example Usage
  41. Tell the AI agent of your choice:
  42. > Open Chrome, go to github.com/angiejones, and take a screenshot.
  43. The agent will call Selenium's APIs to `start_browser`, `navigate`, and `take_screenshot`. No manual scripting or explicit directions needed.
  44. ## Supported Browsers
  45. Chrome, Firefox, Edge, and Safari.
  46. > **Safari note:** Requires macOS. Run `sudo safaridriver --enable` once and enable
  47. > "Allow Remote Automation" in Safari → Settings → Developer. No headless mode.
  48. ---
  49. <details>
  50. <summary><strong>Tools</strong></summary>
  51. ### start_browser
  52. Launches a browser session.
  53. | Parameter | Type | Required | Description |
  54. |-----------|------|----------|-------------|
  55. | browser | string | Yes | `chrome`, `firefox`, `edge`, or `safari` |
  56. | options | object | No | `{ headless: boolean, arguments: string[] }` |
  57. ### navigate
  58. Navigates to a URL.
  59. | Parameter | Type | Required | Description |
  60. |-----------|------|----------|-------------|
  61. | url | string | Yes | URL to navigate to |
  62. ### interact
  63. Performs a mouse action on an element.
  64. | Parameter | Type | Required | Description |
  65. |-----------|------|----------|-------------|
  66. | action | string | Yes | `click`, `doubleclick`, `rightclick`, or `hover` |
  67. | by | string | Yes | Locator strategy: `id`, `css`, `xpath`, `name`, `tag`, `class` |
  68. | value | string | Yes | Value for the locator strategy |
  69. | timeout | number | No | Max wait in ms (default: 10000) |
  70. ### send_keys
  71. Types text into an element. Clears the field first.
  72. | Parameter | Type | Required | Description |
  73. |-----------|------|----------|-------------|
  74. | by | string | Yes | Locator strategy |
  75. | value | string | Yes | Locator value |
  76. | text | string | Yes | Text to enter |
  77. | timeout | number | No | Max wait in ms (default: 10000) |
  78. ### get_element_text
  79. Gets the text content of an element.
  80. | Parameter | Type | Required | Description |
  81. |-----------|------|----------|-------------|
  82. | by | string | Yes | Locator strategy |
  83. | value | string | Yes | Locator value |
  84. | timeout | number | No | Max wait in ms (default: 10000) |
  85. ### get_element_attribute
  86. Gets an attribute value from an element.
  87. | Parameter | Type | Required | Description |
  88. |-----------|------|----------|-------------|
  89. | by | string | Yes | Locator strategy |
  90. | value | string | Yes | Locator value |
  91. | attribute | string | Yes | Attribute name (e.g., `href`, `value`, `class`) |
  92. | timeout | number | No | Max wait in ms (default: 10000) |
  93. ### press_key
  94. Presses a keyboard key.
  95. | Parameter | Type | Required | Description |
  96. |-----------|------|----------|-------------|
  97. | key | string | Yes | Key to press (e.g., `Enter`, `Tab`, `a`) |
  98. ### upload_file
  99. Uploads a file via a file input element.
  100. | Parameter | Type | Required | Description |
  101. |-----------|------|----------|-------------|
  102. | by | string | Yes | Locator strategy |
  103. | value | string | Yes | Locator value |
  104. | filePath | string | Yes | Absolute path to the file |
  105. | timeout | number | No | Max wait in ms (default: 10000) |
  106. ### take_screenshot
  107. Captures a screenshot of the current page.
  108. | Parameter | Type | Required | Description |
  109. |-----------|------|----------|-------------|
  110. | outputPath | string | No | Save path. If omitted, returns base64 image data. |
  111. ### close_session
  112. Closes the current browser session. No parameters.
  113. ### execute_script
  114. Executes JavaScript in the browser. Use for advanced interactions not covered by other tools (e.g., drag and drop, scrolling, reading computed styles, DOM manipulation).
  115. | Parameter | Type | Required | Description |
  116. |-----------|------|----------|-------------|
  117. | script | string | Yes | JavaScript code to execute |
  118. | args | array | No | Arguments accessible via `arguments[0]`, etc. |
  119. ### window
  120. Manages browser windows and tabs.
  121. | Parameter | Type | Required | Description |
  122. |-----------|------|----------|-------------|
  123. | action | string | Yes | `list`, `switch`, `switch_latest`, or `close` |
  124. | handle | string | No | Window handle (required for `switch`) |
  125. ### frame
  126. Switches focus to a frame or back to the main page.
  127. | Parameter | Type | Required | Description |
  128. |-----------|------|----------|-------------|
  129. | action | string | Yes | `switch` or `default` |
  130. | by | string | No | Locator strategy (for `switch`) |
  131. | value | string | No | Locator value (for `switch`) |
  132. | index | number | No | Frame index, 0-based (for `switch`) |
  133. | timeout | number | No | Max wait in ms (default: 10000) |
  134. ### alert
  135. Handles browser alert, confirm, or prompt dialogs.
  136. | Parameter | Type | Required | Description |
  137. |-----------|------|----------|-------------|
  138. | action | string | Yes | `accept`, `dismiss`, `get_text`, or `send_text` |
  139. | text | string | No | Text to send (required for `send_text`) |
  140. | timeout | number | No | Max wait in ms (default: 5000) |
  141. ### add_cookie
  142. Adds a cookie. Browser must be on a page from the cookie's domain.
  143. | Parameter | Type | Required | Description |
  144. |-----------|------|----------|-------------|
  145. | name | string | Yes | Cookie name |
  146. | value | string | Yes | Cookie value |
  147. | domain | string | No | Cookie domain |
  148. | path | string | No | Cookie path |
  149. | secure | boolean | No | Secure flag |
  150. | httpOnly | boolean | No | HTTP-only flag |
  151. | expiry | number | No | Unix timestamp |
  152. ### get_cookies
  153. Gets cookies. Returns all or a specific one by name.
  154. | Parameter | Type | Required | Description |
  155. |-----------|------|----------|-------------|
  156. | name | string | No | Cookie name. Omit for all cookies. |
  157. ### delete_cookie
  158. Deletes cookies. Deletes all or a specific one by name.
  159. | Parameter | Type | Required | Description |
  160. |-----------|------|----------|-------------|
  161. | name | string | No | Cookie name. Omit to delete all. |
  162. ### diagnostics
  163. Gets browser diagnostics captured via WebDriver BiDi (auto-enabled when supported).
  164. | Parameter | Type | Required | Description |
  165. |-----------|------|----------|-------------|
  166. | type | string | Yes | `console`, `errors`, or `network` |
  167. | clear | boolean | No | Clear buffer after returning (default: false) |
  168. </details>
  169. <details>
  170. <summary><strong>Resources</strong></summary>
  171. MCP resources provide read-only data that clients can access without calling a tool.
  172. ### browser-status://current
  173. Returns the current browser session status (active session ID or "no active session").
  174. | Property | Value |
  175. |----------|-------|
  176. | MIME type | `text/plain` |
  177. | Requires browser | No |
  178. ### accessibility://current
  179. Returns an accessibility tree snapshot of the current page — a compact, structured JSON representation of interactive elements and text content. Much smaller than full HTML. Useful for understanding page layout and finding elements to interact with.
  180. | Property | Value |
  181. |----------|-------|
  182. | MIME type | `application/json` |
  183. | Requires browser | Yes |
  184. </details>
  185. ---
  186. <details>
  187. <summary><strong>Development</strong></summary>
  188. ### Setup
  189. ```bash
  190. git clone https://github.com/angiejones/mcp-selenium.git
  191. cd mcp-selenium
  192. npm install
  193. ```
  194. ### Run Tests
  195. ```bash
  196. npm test
  197. ```
  198. Requires Chrome + chromedriver on PATH. Tests run headless.
  199. ### Install via Smithery
  200. ```bash
  201. npx -y @smithery/cli install @angiejones/mcp-selenium --client claude
  202. ```
  203. ### Install globally
  204. ```bash
  205. npm install -g @angiejones/mcp-selenium
  206. mcp-selenium
  207. ```
  208. </details>
  209. ## License
  210. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.