Skip to main content
Glama

browserbase_stagehand_act

Execute specific web page interactions like clicking buttons or typing text through cloud browser automation with AI commands.

Instructions

Performs an action on a web page element. Act actions should be as atomic and specific as possible, i.e. "Click the sign in button" or "Type 'hello' into the search input". AVOID actions that are more than one step, i.e. "Order me pizza" or "Send an email to Paul asking him to call me".

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYesThe action to perform. Should be as atomic and specific as possible, i.e. 'Click the sign in button' or 'Type 'hello' into the search input'. AVOID actions that are more than one step, i.e. 'Order me pizza' or 'Send an email to Paul asking him to call me'. The instruction should be just as specific as possible, and have a strong correlation to the text on the page. If unsure, use observe before using act.
variablesNoVariables used in the action template. ONLY use variables if you're dealing with sensitive data or dynamic content. For example, if you're logging in to a website, you can use a variable for the password. When using variables, you MUST have the variable key in the action template. For example: {"action": "Fill in the password", "variables": {"password": "123456"}}

Implementation Reference

  • The handler function `handleAct` that performs the browser action using Stagehand's `page.act()` method.
    async function handleAct( context: Context, params: ActInput, ): Promise<ToolResult> { const action = async (): Promise<ToolActionResult> => { try { const stagehand = await context.getStagehand(); await stagehand.page.act({ action: params.action, variables: params.variables, }); return { content: [ { type: "text", text: `Action performed: ${params.action}`, }, ], }; } catch (error) { const errorMsg = error instanceof Error ? error.message : String(error); throw new Error(`Failed to perform action: ${errorMsg}`); } }; return { action, waitForNetwork: false, }; }
  • The tool schema definition including the name 'browserbase_stagehand_act', description, and reference to input schema.
    const actSchema: ToolSchema<typeof ActInputSchema> = { name: "browserbase_stagehand_act", description: "Performs an action on a web page element. Act actions should be as atomic and " + 'specific as possible, i.e. "Click the sign in button" or "Type \'hello\' into the search input". ' + 'AVOID actions that are more than one step, i.e. "Order me pizza" or "Send an email to Paul ' + 'asking him to call me".', inputSchema: ActInputSchema, };
  • The Zod input schema `ActInputSchema` defining the `action` string and optional `variables` object.
    const ActInputSchema = z.object({ action: z .string() .describe( "The action to perform. Should be as atomic and specific as possible, " + "i.e. 'Click the sign in button' or 'Type 'hello' into the search input'. AVOID actions that are more than one " + "step, i.e. 'Order me pizza' or 'Send an email to Paul asking him to call me'. The instruction should be just as specific as possible, " + "and have a strong correlation to the text on the page. If unsure, use observe before using act.", ), variables: z .object({}) .optional() .describe( "Variables used in the action template. ONLY use variables if you're dealing " + "with sensitive data or dynamic content. For example, if you're logging in to a website, " + "you can use a variable for the password. When using variables, you MUST have the variable " + 'key in the action template. For example: {"action": "Fill in the password", "variables": {"password": "123456"}}', ), });
  • The `actTool` is included in the `TOOLS` array export, making it available for registration in the MCP server.
    export const TOOLS = [ ...multiSessionTools, ...sessionTools, navigateTool, actTool, extractTool, observeTool, screenshotTool, getUrlTool, ];
  • src/index.ts:196-226 (registration)
    Generic tool registration loop that registers all tools from the `TOOLS` array with the MCP server using `server.tool()`, including 'browserbase_stagehand_act'.
    const tools: MCPToolsArray = [...TOOLS]; // Register each tool with the Smithery server tools.forEach((tool) => { if (tool.schema.inputSchema instanceof z.ZodObject) { server.tool( tool.schema.name, tool.schema.description, tool.schema.inputSchema.shape, async (params: z.infer<typeof tool.schema.inputSchema>) => { try { const result = await context.run(tool, params); return result; } catch (error) { const errorMessage = error instanceof Error ? error.message : String(error); process.stderr.write( `[Smithery Error] ${new Date().toISOString()} Error running tool ${tool.schema.name}: ${errorMessage}\n`, ); throw new Error( `Failed to run tool '${tool.schema.name}': ${errorMessage}`, ); } }, ); } else { console.warn( `Tool "${tool.schema.name}" has an input schema that is not a ZodObject. Schema type: ${tool.schema.inputSchema.constructor.name}`, ); } });

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/RonsDad/mcp-server-browserbase'

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