ultimate-playwright-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AGENT_ID | No | Optional agent ID for logging/debugging. | |
| KEEP_ALIVE | No | Auto-restart daemon-managed Chrome if it exits. Set to 'false' to disable. Default: disabled. | |
| CDP_ENDPOINT | No | CDP endpoint URL (e.g., http://localhost:9222). If omitted, daemon-managed Chrome is started lazily. | |
| CHECKPOINT_OUTPUT_DIR | No | Root directory for checkpoint manifests, artifacts, and reports. |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| browser_tab_groupA | Manage tab groups for session isolation. Multiple users/agents sharing one browser MUST create a tab group first, then pass the groupId to browser_tabs and other tools. This ensures each session only sees and controls its own tabs. Actions:
⚡ IMPORTANT: Always create a tab group before opening tabs with browser_tabs. |
| browser_tabsA | Manage browser tabs. When using tab groups (recommended for multi-user), pass groupId to scope operations to your group's tabs only. Actions:
⚡ IMPORTANT: Create a tab group first for multi-user isolation. Ungrouped tabs remain available as a fallback for local manual testing. |
| browser_navigateA | Navigate to a URL in a specific tab. Use targetId from browser_tabs to specify which tab. |
| browser_snapshotA | Capture accessibility tree snapshot of the current page. Returns element references (e1, e2, etc.) that can be used with other browser tools like click, type, etc. |
| browser_clickB | Click an element by its ref (e1, e2, etc. from snapshot) |
| browser_typeC | Type text into an element |
| browser_hoverC | Hover over an element |
| browser_press_keyC | Press a keyboard key |
| browser_fill_formA | Fill multiple form fields at once |
| browser_wait_forB | Wait for a condition (text, selector, load state, time, etc.) |
| browser_evaluateA | Execute JavaScript in the page context via Playwright's page.evaluate(). Use for interacting with elements not in the accessibility snapshot (portal divs, framework overlays, shadow DOM). Can run arbitrary JS — click hidden elements, extract data, manipulate the DOM. Optionally scope to a specific element via ref. |
| browser_screenshotA | Take a screenshot of the current page or a specific element. By default saves to file and returns the path (saves context window tokens). Use |
| browser_checkpointC | Capture a structured checkpoint for the current page or a specific tab. Stores checkpoint artifacts and a manifest under the server-managed checkpoint directory. |
| browser_checkpoint_reportA | Generate an HTML, Markdown, or MDX report from stored MCP checkpoint manifests. |
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 14 tools
Each tool serves a distinct browser automation action (e.g., click, type, navigate, snapshot). Potential overlaps like browser_click vs. browser_hover are clearly differentiated by operation type, and browser_evaluate handles cases outside the snapshot tree.
All tools follow a consistent 'browser_verb_noun' pattern using snake_case. For example, browser_click, browser_navigate, browser_tab_group. No mixing of conventions.
With 14 tools, the server covers core browser automation tasks without being bloated. The count feels well-scoped for its purpose.
The tool set covers essential browser actions (navigation, interaction, snapshot, screenshots, tabs, checkpoints). Minor gaps exist, such as no explicit scroll or file upload, but these are advanced and not critical for most automation workflows.