Skip to main content
Glama
BrowserGenie

BrowserGenie MCP Server

by BrowserGenie

read_scripts

Read JavaScript sources loaded on a webpage. Retrieve all scripts or a specific one by URL for analysis or debugging.

Instructions

Read JavaScript sources loaded on the page. Returns all scripts or a specific one by URL.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlNoSpecific script URL to read (returns all if omitted)
tabIdNoTarget tab ID (defaults to active tab)
apiKeyNoAPI key for authentication

Implementation Reference

  • The handler function that executes the 'read_scripts' tool logic. It sends a 'read_scripts' command via the WebSocket bridge and returns the result.
      async ({ url, tabId, apiKey }) => {
        const result = await bridge.sendCommand({
          command: 'read_scripts',
          params: { url },
          tabId,
          apiKey,
        });
        if (!result.success) {
          return { content: [{ type: 'text', text: `Error: ${result.error?.message}` }], isError: true };
        }
        return { content: [{ type: 'text', text: JSON.stringify(result.data, null, 2) }] };
      }
    );
  • Zod schema defining the input parameters for 'read_scripts': url (optional string), tabId (optional number), apiKey (optional string).
    {
      url: z.string().optional().describe('Specific script URL to read (returns all if omitted)'),
      tabId: z.number().optional().describe('Target tab ID (defaults to active tab)'),
      apiKey: z.string().optional().describe('API key for authentication'),
    },
  • Registration of the 'read_scripts' tool via server.tool() call, with description 'Read JavaScript sources loaded on the page. Returns all scripts or a specific one by URL.'
    server.tool(
      'read_scripts',
  • Import of registerDevtoolsSourcesTools from devtools-sources.ts, which is called by registerAllTools in the central tool registration.
    import { registerDevtoolsSourcesTools } from './devtools-sources.js';
    import { registerDevtoolsModifyTools } from './devtools-modify.js';
    import { registerDevtoolsNetworkTools } from './devtools-network.js';
    import { registerDevtoolsStorageTools } from './devtools-storage.js';
    import { registerDevtoolsConsoleTools } from './devtools-console.js';
    
    import { registerAccessibilityTools } from './accessibility.js';
    import { registerEmulationTools } from './emulation.js';
    import { registerElementTools } from './elements.js';
    import { registerAuditTools } from './audit.js';
    import { registerInteractionTools } from './interaction.js';
    import { registerMonitoringTools } from './monitoring.js';
    import { registerQaTools } from './qa.js';
    import { registerGestureTools } from './gestures.js';
    import { registerMacroTools } from './macros.js';
    import { registerVisualRegressionTools } from './visual-regression.js';
    
    export function registerAllTools(server: McpServer, bridge: WebSocketBridge) {
      registerNavigationTools(server, bridge);
      registerTabManagementTools(server, bridge);
      registerKeyboardTools(server, bridge);
      registerScreenshotTools(server, bridge);
      registerClickTools(server, bridge);
      registerInputTools(server, bridge);
      registerDragDropTools(server, bridge);
      registerHoverTools(server, bridge);
    
      registerDevtoolsSourcesTools(server, bridge);
  • The WebSocketBridge.sendCommand() method used by the handler to send the 'read_scripts' command to the browser extension.
    async sendCommand(cmd: BridgeCommand): Promise<BridgeResponse> {
      if (!this.isConnected()) {
        return {
          success: false,
          error: {
            code: 'NOT_CONNECTED',
            message: 'Chrome extension is not connected. Ensure the extension is installed, enabled, and the browser is running.',
          },
        };
      }
    
      const id = crypto.randomUUID();
      const timeout = cmd.timeout ?? DEFAULT_TIMEOUT;
    
      return new Promise<BridgeResponse>((resolve, reject) => {
        const timer = setTimeout(() => {
          this.pending.delete(id);
          resolve({
            success: false,
            error: {
              code: 'TIMEOUT',
              message: `Command '${cmd.command}' timed out after ${timeout}ms`,
            },
          });
        }, timeout);
    
        this.pending.set(id, { resolve, reject, timer });
    
        const message = {
          id,
          type: 'request',
          command: cmd.command,
          params: cmd.params,
          tabId: cmd.tabId,
          apiKey: cmd.apiKey,
          timestamp: Date.now(),
        };
    
        this.client!.send(JSON.stringify(message));
      });
    }
Behavior2/5

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

With no annotations, the description must disclose behavioral traits. It mentions a read operation but does not address limitations (e.g., cross-origin restrictions), whether it returns runtime state or static source, or side effects. Essential safety context is missing.

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?

Two short sentences efficiently convey the core action and return behavior. No unnecessary information, though it could be structured more compactly.

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?

Without an output schema, the description should explain the return format or structure. It only says 'returns all scripts or a specific one' without indicating whether the response includes source code, metadata, or how to handle missing scripts. Errors and edge cases are not addressed.

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?

Schema coverage is 100%, so baseline is 3. The description mainly restates the URL parameter behavior already covered in the schema, adding no new semantics for tabId or apiKey.

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?

Clearly states the tool reads JavaScript sources from the page, with explicit specification of retrieving all scripts or filtering by URL. This distinguishes it from sibling tools like read_stylesheets or read_page_html.

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 execute_javascript or get_network_request_detail. No conditions for use or exclusions are provided.

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/BrowserGenie/mcp'

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