Skip to main content
Glama
merajmehrabi

Puppeteer MCP Server

by merajmehrabi

puppeteer_evaluate

Execute custom JavaScript code directly in the browser console to test scripts and interact with web pages.

Instructions

Execute JavaScript in the browser console

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
scriptYesJavaScript code to execute

Implementation Reference

  • Schema definition for the puppeteer_evaluate tool. It has name 'puppeteer_evaluate', description 'Execute JavaScript in the browser console', and expects a required 'script' string parameter as input.
    {
      name: "puppeteer_evaluate",
      description: "Execute JavaScript in the browser console",
      inputSchema: {
        type: "object",
        properties: {
          script: { type: "string", description: "JavaScript code to execute" },
        },
        required: ["script"],
      },
    },
  • Handler implementation for puppeteer_evaluate. Sets up console listener, executes the provided JavaScript via page.evaluate() wrapped in an async IIFE, captures console output, and returns both the result and console logs.
    case "puppeteer_evaluate":
      try {
        // Set up console listener
        const logs: string[] = [];
        const consoleListener = (message: any) => {
          logs.push(`${message.type()}: ${message.text()}`);
        };
        
        page.on('console', consoleListener);
        
        // Execute script with proper serialization
        logger.debug('Executing script in browser', { scriptLength: args.script.length });
        
        // Wrap the script in a function that returns a serializable result
        const result = await page.evaluate(`(async () => {
          try {
            const result = (function() { ${args.script} })();
            return result;
          } catch (e) {
            console.error('Script execution error:', e.message);
            return { error: e.message };
          }
        })()`);
        
        // Remove the listener to avoid memory leaks
        page.off('console', consoleListener);
        
        logger.debug('Script execution result', {
          resultType: typeof result,
          hasResult: result !== undefined,
          logCount: logs.length
        });
    
        return {
          content: [{
            type: "text",
            text: `Execution result:\n${JSON.stringify(result, null, 2)}\n\nConsole output:\n${logs.join('\n')}`,
          }],
          isError: false,
        };
      } catch (error) {
        logger.error('Script evaluation failed', { error: error instanceof Error ? error.message : String(error) });
        return {
          content: [{
            type: "text",
            text: `Script execution failed: ${error instanceof Error ? error.message : String(error)}\n\nPossible causes:\n- Syntax error in script\n- Execution timeout\n- Browser security restrictions\n- Serialization issues with complex objects`,
          }],
          isError: true,
        };
      }
  • src/server.ts:35-41 (registration)
    Tool registration in the server. The ListToolsRequestSchema handler exposes TOOLS (which includes puppeteer_evaluate), and the CallToolRequestSchema handler dispatches to handleToolCall which contains the case for 'puppeteer_evaluate'.
    server.setRequestHandler(ListToolsRequestSchema, async () => ({
      tools: TOOLS,
    }));
    
    server.setRequestHandler(CallToolRequestSchema, async (request) =>
      handleToolCall(request.params.name, request.params.arguments ?? {}, state, server)
    );

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.1/5.0
Behavior2/5

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

No annotations are provided, so the description bears full responsibility. It mentions execution in the browser console but does not specify whether the script runs synchronously, how return values are handled, or potential side effects on the page state.

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

Conciseness4/5

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

A single, direct sentence that immediately conveys the tool's purpose. It is front-loaded and contains no unnecessary words.

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

Completeness2/5

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

The description is minimal given the tool's potential complexity. It does not explain what the execution returns, how to handle asynchronous code, or any security considerations. No output schema exists to compensate.

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

Parameters3/5

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

The single parameter 'script' has a clear description in the schema ('JavaScript code to execute'), and the tool description adds no extra meaning. With 100% schema coverage, baseline 3 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 ('Execute') and the target ('JavaScript in the browser console'), distinguishing it from sibling tools that perform specific UI interactions like clicking, filling, or navigating.

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

Usage Guidelines2/5

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

No guidance on when to use this tool versus alternatives such as puppeteer_click or puppeteer_fill. The description lacks context about typical use cases for executing arbitrary JavaScript.

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