mcp-playwright-automation
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_SCREENSHOT_DIR | No | Directory to save screenshots. Relative names are resolved against the screenshots/ folder at the project root; override it with this environment variable. | screenshots/ |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| navigateB | Navigates to a specific URL |
| clickB | Clicks an element on the page |
| fillFormC | Fills a form field |
| extractDataB | Extracts the text of an element on the page |
| getPageContentA | Gets the full HTML content of the page |
| screenshotC | Takes a screenshot of the page |
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 6 tools
Each tool targets a distinct browser action: navigation, clicking, form filling, data extraction, content retrieval, and screenshots. No overlap in purpose, so agents can clearly differentiate.
Naming mixes conventions: snake_case verbs (navigate, click, screenshot) and camelCase verb_noun (fillForm, extractData, getPageContent). The pattern is inconsistent, with some tools using single verbs and others using verb_noun, and differing case styles.
Six tools form a tight, well-scoped set for basic browser automation, each earning its place. This is within the ideal 3-15 range.
The surface covers core browsing workflows (navigate, interact, extract, screenshot) but lacks common operations like waiting for elements, hovering, selecting options, or scrolling. Basic tasks are possible, but advanced automation scenarios would require workarounds.