DevTools Lens MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| browser_launchC | Launch a new Chromium instance and start collecting DevTools events. |
| browser_connectB | Connect to an existing Chromium remote-debugging endpoint. |
| browser_navigateC | Navigate the active page and wait for the selected lifecycle event. |
| browser_get_page_infoB | Return page URL, viewport, loading state, and resource counts. |
| browser_get_console_logsB | Query buffered console messages from the entire browser session. |
| browser_get_console_errorsB | Return grouped console errors and uncaught exceptions with likely categories. |
| browser_get_network_requestsC | Query buffered network request history with diagnostic filters. |
| browser_get_failed_requestsB | Return failed HTTP and transport requests with likely causes. |
| browser_get_request_detailsC | Inspect one request, including a bounded textual response body when available. |
| browser_inspect_elementB | Inspect an element, its layout, computed styles, and accessible identity. |
| browser_get_dom_snapshotC | Capture a compact agent-friendly DOM snapshot. |
| browser_clickB | Click an element and optionally capture resulting DOM, console, network, and URL changes. |
| browser_fillB | Fill an input, textarea, or contenteditable element without exposing passwords. |
| browser_selectC | Select an option by value, label, or index. |
| browser_press_keyB | Press a keyboard key or chord on the page or a selected element. |
| browser_screenshotA | Capture a page or element screenshot in the controlled output directory. |
| browser_get_accessibility_issuesB | Run axe-core accessibility checks and return actionable issues. |
| browser_compare_domC | Compare two compact DOM snapshots. |
| browser_closeB | Safely close a browser session. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 19 tools
Most tools have clearly distinct purposes, though some overlap exists between related inspection tools (e.g., get_dom_snapshot vs inspect_element, get_network_requests vs get_failed_requests vs get_request_details). Descriptions adequately distinguish them, but an agent might occasionally hesitate when choosing between similar-sounding network or DOM tools.
All tools follow a consistent snake_case pattern with the 'browser_' prefix, and the verb-noun structure is uniform (get_*, click, fill, select, press_key, launch, connect, navigate, screenshot, compare_dom, close). This makes the tool set highly predictable and easy to navigate.
With 19 tools, the server is on the heavier side, bordering on the 16-25 range that feels dense. However, each tool addresses a specific DevTools need, so the count is justifiable, but it still feels a bit large for a focused lens. Streamlining could help.
The tool set covers a broad range of browser automation and DevTools activities including navigation, interaction, DOM inspection, network and console diagnostics, screenshots, accessibility, and session management. Minor gaps exist such as no explicit browser history navigation or JavaScript evaluation, but the core workflows are well supported.