parallel-browser-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ANCHOR_API_KEY | No | Anchor API key (required for anchor provider). | |
| BROWSER_MCP_CONFIG | No | JSON configuration string for providers (e.g., defaultProvider, provider-specific settings). | |
| PLAYWRIGHT_CHANNEL | No | Playwright channel. | |
| BROWSERBASE_API_KEY | No | Browserbase API key (required for browserbase provider). | |
| BROWSERBASE_PERSIST | No | Browserbase persist setting. | |
| CLOUDFLARE_API_TOKEN | No | Cloudflare API token (required for cloudflare provider). | |
| CLOUDFLARE_ACCOUNT_ID | No | Cloudflare account ID (required for cloudflare provider). | |
| BROWSERBASE_CONTEXT_ID | No | Browserbase context ID. | |
| BROWSERBASE_KEEP_ALIVE | No | Browserbase keep alive setting. | |
| BROWSERBASE_PROJECT_ID | No | Browserbase project ID (can also be set in config). | |
| BROWSER_MCP_CONFIG_PATH | No | Path to a JSON configuration file. | |
| PLAYWRIGHT_EXECUTABLE_PATH | No | Path to Playwright executable. | |
| PLAYWRIGHT_STORAGE_STATE_PATH | No | Path to Playwright storage state file. |
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 |
|---|---|
| start_sessionC | Start a browser session using the configured provider. |
| close_sessionB | Close a browser session by numeric session ID. |
| close_all_sessionsA | Close all active browser sessions. |
| get_sessionsA | List all active browser sessions. |
| browser_navigateD | Navigate the session page to a URL. |
| browser_go_backC | Go back in browser history. |
| browser_clickC | Click an element by selector. |
| browser_fillC | Fill a field with text. |
| browser_fill_formC | Fill multiple form fields. |
| browser_screenshotC | Capture a screenshot of the current page. |
| browser_snapshotC | Return a structured page snapshot. |
| browser_hoverC | Hover over an element by selector. |
| browser_dragC | Drag from one element to another. |
| browser_select_optionC | Select options in a select element. |
| browser_generate_locatorC | Generate locator suggestions for an element. |
| browser_get_page_structureC | Return a readable page structure summary. |
| browser_dom_queryC | Query element presence, count, and state without waiting. |
| browser_evaluateC | Run JavaScript in the page context. |
| browser_keyboard_pressC | Press a keyboard key or key chord. |
| browser_keyboard_typeC | Type text into the active page. |
| browser_mouse_moveC | Move the mouse to viewport coordinates. |
| browser_mouse_click_xyC | Click at viewport coordinates. |
| browser_mouse_dragD | Drag the mouse from one point to another. |
| browser_upload_fileC | Upload files to a file input. |
| browser_wait_for_selectorC | Wait for a selector to reach a state. |
| browser_wait_for_timeoutC | Wait a fixed number of milliseconds. |
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 26 tools
Most browser actions are individually clear, but several near-overlapping pairs exist: browser_snapshot, browser_get_page_structure, and browser_dom_query all describe page/DOM inspection, while browser_fill, browser_keyboard_type, browser_click, and browser_mouse_click_xy cover similar input territory. Descriptions reduce some ambiguity, but an agent could still easily select the wrong tool.
Session tools follow a clean verb_noun pattern like start_session and close_session, while browser actions consistently use a browser_ prefix followed by descriptive verbs. The mixed prefixes are minor and the naming remains predictable and readable.
With 26 tools, this server sits above the 25+ threshold and feels too heavy for a single MCP surface. Several mouse, keyboard, and DOM primitives could be consolidated or split into a separate server without losing functionality.
The toolset covers the core browser automation lifecycle well: navigation, DOM interaction, form filling, mouse/keyboard input, screenshots, uploads, waits, and session management. Notable gaps like tab/window management, cookies, and frame handling are missing, but agents can often work around them via browser_evaluate or separate sessions.