Skip to main content
Glama
Lokii0911
by Lokii0911

browser_start

Initiate a Selenium browser session for automated testing or web scraping. Ensures a browser instance is active before performing navigation, interaction, or screenshot tasks.

Instructions

Start a Selenium browser session if one is not already running.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • BrowserManager.start() - The actual handler logic: creates a new Selenium WebDriver session if none exists, configures it, and returns the current browser state.
    def start(self) -> BrowserState:
        with self._lock:
            if self._driver is None:
                self._settings.default_download_dir.mkdir(parents=True, exist_ok=True)
                self._driver = self._create_driver()
                self._configure_driver(self._driver)
            return self.state()
  • browser_start() - The MCP tool decorator that registers the tool and delegates to BrowserManager.start() via the _run helper.
    @mcp.tool()
    def browser_start() -> dict[str, Any]:
        """Start a Selenium browser session if one is not already running."""
        return _run("browser_start", browser.start)
  • _run() helper - wraps the handler invocation with error handling and dict serialization.
    def _run(action: str, func: Any, *args: Any, **kwargs: Any) -> Any:
        try:
            return _as_dict(func(*args, **kwargs))
        except BrowserError:
            logger.exception("Browser action failed: %s", action)
            raise
        except Exception as exc:
            logger.exception("Unexpected Selenium MCP error during %s", action)
            raise BrowserError(f"{action} failed: {exc}") from exc
  • BrowserState - the return type/response schema for browser_start.
    class BrowserState(BaseModel):
        session_id: str | None
        current_url: str | None
        title: str | None
        window_handles: list[str]
        active_window_handle: str | None
  • The @mcp.tool() decorator registers browser_start as an MCP tool.
    @mcp.tool()
    def browser_start() -> dict[str, Any]:
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must convey behavioral traits. It mentions the condition about an existing session but does not detail what happens if one is already running (e.g., no-op vs error), nor does it cover side effects like clearing cookies or state. Partial but not fully transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no unnecessary words. Every part contributes to understanding the tool's purpose and condition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simplicity of the tool (no parameters, output schema exists), the description is minimally adequate. However, it omits details like return value behavior, potential blocking, or what happens if a session is already running. It is not fully comprehensive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has no parameters, so the description cannot add parameter meaning. Baseline is 4 for zero-parameter tools, and the description provides behavioral context beyond the empty schema, such as the conditional start.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (start) and resource (Selenium browser session), and includes a condition (if one is not already running) that adds specificity. It effectively distinguishes from sibling tools like browser_stop and browser_reset.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use (when no session is running) but does not explicitly state when not to use or what alternatives exist for handling existing sessions. It gives some usage context but lacks exclusions or alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Lokii0911/SeleniumMCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server