Skip to main content
Glama

browserbase_session_close

Properly shuts down browser sessions by terminating the Stagehand instance to handle cleanup and stop recordings.

Instructions

Closes the current Browserbase session by properly shutting down the Stagehand instance, which handles browser cleanup and terminates the session recording.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • The handleCloseSession function that implements the tool's core logic: gets the current session, closes the Stagehand instance if available, cleans up the session tracking, resets the context's current session ID to default, and returns appropriate success or info messages with error handling.
    async function handleCloseSession(context: Context): Promise<ToolResult> {
      const action = async (): Promise<ToolActionResult> => {
        // Store the current session ID before it's potentially changed.
        const previousSessionId = context.currentSessionId;
        let stagehandClosedSuccessfully = false;
        let stagehandCloseErrorMessage = "";
    
        // Step 1: Attempt to get the session and close Stagehand
        let browserbaseSessionId: string | undefined;
        try {
          const session = await getSession(
            previousSessionId,
            context.config,
            false,
          );
    
          if (session && session.stagehand) {
            // Store the actual Browserbase session ID for the replay URL
            browserbaseSessionId = session.sessionId;
    
            process.stderr.write(
              `[tool.closeSession] Attempting to close Stagehand for session: ${previousSessionId || "default"} (Browserbase ID: ${browserbaseSessionId})`,
            );
    
            // Use Stagehand's close method which handles browser cleanup properly
            await session.stagehand.close();
            stagehandClosedSuccessfully = true;
    
            process.stderr.write(
              `[tool.closeSession] Stagehand and browser connection for session (${previousSessionId}) closed successfully.`,
            );
    
            // Clean up the session from tracking
            await cleanupSession(previousSessionId);
    
            if (browserbaseSessionId) {
              process.stderr.write(
                `[tool.closeSession] View session replay at https://www.browserbase.com/sessions/${browserbaseSessionId}`,
              );
            }
          } else {
            process.stderr.write(
              `[tool.closeSession] No Stagehand instance found for session: ${previousSessionId || "default/unknown"}`,
            );
          }
        } catch (error: unknown) {
          stagehandCloseErrorMessage =
            error instanceof Error ? error.message : String(error);
          process.stderr.write(
            `[tool.closeSession] Error retrieving or closing Stagehand (session ID was ${previousSessionId || "default/unknown"}): ${stagehandCloseErrorMessage}`,
          );
        }
    
        // Step 2: Always reset the context's current session ID to default
        const oldContextSessionId = context.currentSessionId;
        context.currentSessionId = defaultSessionId;
        process.stderr.write(
          `[tool.closeSession] Session context reset to default. Previous context session ID was ${oldContextSessionId || "default/unknown"}.`,
        );
    
        // Step 3: Determine the result message
        if (stagehandCloseErrorMessage && !stagehandClosedSuccessfully) {
          throw new Error(
            `Failed to close the Stagehand session (session ID in context was ${previousSessionId || "default/unknown"}). Error: ${stagehandCloseErrorMessage}. Session context has been reset to default.`,
          );
        }
    
        if (stagehandClosedSuccessfully) {
          let successMessage = `Browserbase session (${previousSessionId || "default"}) closed successfully via Stagehand. Context reset to default.`;
          if (browserbaseSessionId && previousSessionId !== defaultSessionId) {
            successMessage += ` View replay at https://www.browserbase.com/sessions/${browserbaseSessionId}`;
          }
          return { content: [{ type: "text", text: successMessage }] };
        }
    
        // No Stagehand instance was found
        let infoMessage =
          "No active Stagehand session found to close. Session context has been reset to default.";
        if (previousSessionId && previousSessionId !== defaultSessionId) {
          infoMessage = `No active Stagehand session found for session ID '${previousSessionId}'. The context has been reset to default.`;
        }
        return { content: [{ type: "text", text: infoMessage }] };
      };
    
      return {
        action: action,
        waitForNetwork: false,
      };
    }
  • Defines the input schema (empty, no params needed) and the tool schema including the unique name 'browserbase_session_close', description, and inputSchema reference.
    const CloseSessionInputSchema = z.object({});
    
    const closeSessionSchema: ToolSchema<typeof CloseSessionInputSchema> = {
      name: "browserbase_session_close",
      description:
        "Closes the current Browserbase session by properly shutting down the Stagehand instance, which handles browser cleanup and terminates the session recording.",
      inputSchema: CloseSessionInputSchema,
    };
  • Registers the tool by creating the closeSessionTool object that combines the schema and handler function, and exports it within the array of session tools.
    const closeSessionTool: Tool<typeof CloseSessionInputSchema> = {
      capability: "core",
      schema: closeSessionSchema,
      handle: handleCloseSession,
    };
    
    export default [createSessionTool, closeSessionTool];
  • Aggregates all tools, including sessionTools (which contains browserbase_session_close), into the central TOOLS array exported for use in MCP server setup.
    export const TOOLS = [
      ...multiSessionTools,
      ...sessionTools,
      navigateTool,
      actTool,
      extractTool,
      observeTool,
      screenshotTool,
      getUrlTool,
    ];
  • src/index.ts:192-222 (registration)
    Final MCP server registration: loops over TOOLS array and calls server.tool() for each, using the tool's schema.name ('browserbase_session_close'), description, input schema shape, and a wrapper handler that invokes context.run(tool, params).
    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}`,
        );
      }
    });

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.0.0
    • addedInput schema / $schema
      Added value: +"http://json-schema.org/draft-07/schema#"
    • addedInput schema / additionalProperties
      Added value: +false
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full burden. It discloses that it handles cleanup and terminates recording, which is good for a close operation. However, it lacks details on idempotency or error behavior if the session is already closed.

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?

A single, well-structured sentence that front-loads the main action and provides necessary context without waste.

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

Completeness5/5

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

For a parameterless close action with no output schema, the description is complete. It explains the side effects (cleanup, recording termination) adequately.

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 tool has no parameters and schema coverage is 100%. The description does not need to add parameter info. Baseline 4 for 0-param tools is appropriate.

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 ('closes'), the resource ('Browserbase session'), and the method ('shutting down Stagehand instance, browser cleanup, terminates recording'). It distinguishes from siblings like browserbase_session_create and multi_browserbase_session_create.

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 this tool should be used after a session is created and is no longer needed, but it does not explicitly state when to use it versus alternatives, nor does it provide exclusion criteria or mention prerequisites.

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