angiejones/mcp-selenium
mcp-selenium is hosted online, so all tools can be tested directly either in theInspector tabor in theOnline Client.
If you are the rightful owner of mcp-selenium and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
A Model Context Protocol (MCP) server implementation for Selenium WebDriver, enabling browser automation through standardized MCP clients.
Try mcp-selenium with chat:
Has a README
Github repo has a README.md.
Has a License
Github repo has license info.
Server can be inspected
View server inspector
Server schema can be extracted
Can get at lease one tool info from the README or server.
Online hosted on MCPHub
Can be automatically deployed by MCPHub.
Has social accounts
Do not have any social accounts.
Claimed by the author or certified by MCPHub
If you are the author, claim authorship
AI Evaluation ReportTotal Score: 1/10
The agent consistently failed to perform the tasks due to tool malfunctions, such as failing to start a browser session or locate elements on a webpage. This indicates significant reliability issues with the tool's functionality, preventing it from executing even basic web automation tasks. The agent's inability to provide valid answers for any of the tasks tested highlights a critical weakness in its current implementation.
Test case 1
Score: 2/10Perform the operation of launching a headless Chrome browser, navigating to https://www.foxnews.com/politics/longtime-biden-aide-testifies-he-stood-earn-up-8m-had-president-won-re-election, capturing a screenshot of the page, and saving it to a specified path.No valid answer is generated due to tool malfunction. The tool failed to start the browser session, and the error message indicates 'No active browser session.' This suggests a malfunction in the tool itself rather than an issue with the task input.
Test case 2
Score: 2/10Perform the operation of launching a headless Firefox browser, navigating to https://en.wikipedia.org/wiki/Interstate_35W_(Minnesota), locating the first paragraph under the 'History' section, and retrieving its text content.No valid answer is generated due to tool malfunction. The tool encountered an error while trying to locate the element containing the first paragraph under the 'History' section. The wait for the element timed out, indicating that it could not find the specified element on the page.
Test case 3
Score: 2/10Perform the operation of launching a headless Chrome browser, navigating to https://www.cnn.com, locating the search input field, entering the text 'latest news', and submitting the search form.Failed to get an answer for the task.
Test case 4
Score: 2/10Perform the operation of launching a headless Chrome browser, navigating to https://en.wikipedia.org/wiki/Main_Page, locating the 'Today's featured article' section, and retrieving its text content.Failed to get an answer for the task.
Test case 5
Score: 2/10Perform the operation of launching a headless Chrome browser, navigating to https://www.cnn.com/business/tech, locating the first article headline, and retrieving its text content.Failed to get an answer for the task.