Skip to main content
Glama

browserbase_session_create

Create or reuse a single cloud browser session for web automation, data extraction, and form interactions with full configuration support.

Instructions

Create or reuse a single cloud browser session using Browserbase with fully initialized Stagehand. WARNING: This tool is for SINGLE browser workflows only. If you need multiple browser sessions running simultaneously (parallel scraping, A/B testing, multiple accounts), use 'multi_browserbase_stagehand_session_create' instead. This creates one browser session with all configuration flags (proxies, stealth, viewport, cookies, etc.) and initializes Stagehand to work with that session. Updates the active session.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sessionIdNoOptional session ID to use/reuse. If not provided or invalid, a new session is created.

Implementation Reference

  • The handler function `handleCreateSession` that executes the tool logic: creates or reuses a Browserbase session using SessionManager, connects Stagehand, logs URLs, and handles errors.
    async function handleCreateSession(
      context: Context,
      params: CreateSessionInput,
    ): Promise<ToolResult> {
      const action = async (): Promise<ToolActionResult> => {
        try {
          const config = context.config; // Get config from context
          let targetSessionId: string;
    
          if (params.sessionId) {
            const projectId = config.browserbaseProjectId || "";
            targetSessionId = `${params.sessionId}_${projectId}`;
            process.stderr.write(
              `[tool.createSession] Attempting to create/assign session with specified ID: ${targetSessionId}`,
            );
          } else {
            targetSessionId = defaultSessionId;
          }
    
          let session: BrowserSession;
          if (targetSessionId === defaultSessionId) {
            session = await ensureDefaultSessionInternal(config);
          } else {
            // When user provides a sessionId, we want to resume that Browserbase session
            session = await createNewBrowserSession(
              targetSessionId,
              config,
              params.sessionId,
            );
          }
    
          if (
            !session ||
            !session.browser ||
            !session.page ||
            !session.sessionId ||
            !session.stagehand
          ) {
            throw new Error(
              `SessionManager failed to return a valid session object with actualSessionId for ID: ${targetSessionId}`,
            );
          }
    
          context.currentSessionId = targetSessionId;
          const bb = new Browserbase({
            apiKey: config.browserbaseApiKey,
          });
          const debugUrl = (await bb.sessions.debug(session.sessionId))
            .debuggerFullscreenUrl;
          process.stderr.write(
            `[tool.connected] Successfully connected to Browserbase session. Internal ID: ${targetSessionId}, Actual ID: ${session.sessionId}`,
          );
    
          process.stderr.write(
            `[SessionManager] Browserbase Live Session View URL: https://www.browserbase.com/sessions/${session.sessionId}`,
          );
    
          process.stderr.write(
            `[SessionManager] Browserbase Live Debugger URL: ${debugUrl}`,
          );
    
          return {
            content: [
              {
                type: "text",
                text: `Browserbase Live Session View URL: https://www.browserbase.com/sessions/${session.sessionId}\nBrowserbase Live Debugger URL: ${debugUrl}`,
              },
            ],
          };
        } catch (error: unknown) {
          const errorMessage =
            error instanceof Error ? error.message : String(error);
          process.stderr.write(
            `[tool.createSession] Action failed: ${errorMessage}`,
          );
          // Re-throw to be caught by Context.run's error handling for actions
          throw new Error(`Failed to create Browserbase session: ${errorMessage}`);
        }
      };
    
      // Return the ToolResult structure expected by Context.run
      return {
        action: action,
        waitForNetwork: false,
      };
    }
  • Zod input schema and tool schema definition including name, description, and input validation for session ID.
    const CreateSessionInputSchema = z.object({
      // Keep sessionId optional, but clarify its role
      sessionId: z
        .string()
        .optional()
        .describe(
          "Optional session ID to use/reuse. If not provided or invalid, a new session is created.",
        ),
    });
    type CreateSessionInput = z.infer<typeof CreateSessionInputSchema>;
    
    const createSessionSchema: ToolSchema<typeof CreateSessionInputSchema> = {
      name: "browserbase_session_create",
      description:
        "Create or reuse a single cloud browser session using Browserbase with fully initialized Stagehand. WARNING: This tool is for SINGLE browser workflows only. If you need multiple browser sessions running simultaneously (parallel scraping, A/B testing, multiple accounts), use 'multi_browserbase_stagehand_session_create' instead. This creates one browser session with all configuration flags (proxies, stealth, viewport, cookies, etc.) and initializes Stagehand to work with that session. Updates the active session.",
      inputSchema: CreateSessionInputSchema,
    };
  • Registration of the session tools (including browserbase_session_create) into the main TOOLS array exported for MCP server.
    export const TOOLS = [
      ...multiSessionTools,
      ...sessionTools,
      navigateTool,
      actTool,
      extractTool,
      observeTool,
      screenshotTool,
      getUrlTool,
    ];
  • src/index.ts:192-222 (registration)
    MCP server registration loop that dynamically registers all tools from TOOLS array, including browserbase_session_create, using server.tool().
    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}`,
        );
      }
    });
  • Helper function `createStagehandInstance` used in session creation, configuring and initializing Stagehand with Browserbase session parameters.
    export const createStagehandInstance = async (
      config: Config,
      params: CreateSessionParams = {},
      sessionId: string,
    ): Promise<Stagehand> => {
      const apiKey = params.apiKey || config.browserbaseApiKey;
      const projectId = params.projectId || config.browserbaseProjectId;
    
      if (!apiKey || !projectId) {
        throw new Error("Browserbase API Key and Project ID are required");
      }
    
      const stagehand = new Stagehand({
        env: "BROWSERBASE",
        apiKey,
        projectId,
        modelName:
          params.modelName || config.modelName || "google/gemini-2.0-flash",
        modelClientOptions: {
          apiKey: config.modelApiKey || process.env.GEMINI_API_KEY,
        },
        ...(params.browserbaseSessionID && {
          browserbaseSessionID: params.browserbaseSessionID,
        }),
        browserbaseSessionCreateParams: {
          projectId,
          proxies: config.proxies,
          keepAlive: config.keepAlive ?? false,
          browserSettings: {
            viewport: {
              width: config.viewPort?.browserWidth ?? 1024,
              height: config.viewPort?.browserHeight ?? 768,
            },
            context: config.context?.contextId
              ? {
                  id: config.context?.contextId,
                  persist: config.context?.persist ?? true,
                }
              : undefined,
            advancedStealth: config.advancedStealth ?? undefined,
          },
          userMetadata: {
            mcp: "true",
          },
        },
        logger: (logLine) => {
          console.error(`Stagehand[${sessionId}]: ${logLine.message}`);
        },
      });
    
      await stagehand.init();
      return stagehand;
    };
Behavior4/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behaviors: it creates or reuses sessions based on sessionId, initializes Stagehand, updates the active session, and includes configuration flags (proxies, stealth, viewport, cookies, etc.). It also warns about the single-session limitation. However, it doesn't mention potential side effects like resource consumption or error handling.

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 well-structured and concise. It front-loads the core purpose, includes a critical warning, specifies when to use alternatives, and details functionality—all in three sentences with zero wasted words.

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

Completeness4/5

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

Given no annotations and no output schema, the description does a good job covering the tool's purpose, usage, and behavior. It explains the parameter semantics and distinguishes from siblings. However, it lacks details on output format or error cases, which would be helpful for a tool with no output schema.

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?

Schema description coverage is 100%, so the schema already documents the sessionId parameter. The description adds value by explaining the semantics: 'Optional session ID to use/reuse. If not provided or invalid, a new session is created.' This clarifies the reuse behavior beyond the schema's basic description.

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 tool's purpose: 'Create or reuse a single cloud browser session using Browserbase with fully initialized Stagehand.' It specifies the verb (create/reuse), resource (browser session), and distinguishes it from sibling tools by emphasizing it's for 'SINGLE browser workflows only.'

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

Usage Guidelines5/5

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

The description provides explicit guidance on when to use this tool vs. alternatives: 'This tool is for SINGLE browser workflows only. If you need multiple browser sessions running simultaneously (parallel scraping, A/B testing, multiple accounts), use 'multi_browserbase_stagehand_session_create' instead.' It clearly defines the scope and names the alternative tool.

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/vaibhavAtlys/mcp-server-browserbase'

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