Skip to main content
Glama

browser_network_requests

Capture and analyze network traffic from browser sessions to monitor HTTP requests, responses, and performance data during web interactions.

Instructions

Get network requests

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • index.js:468-473 (registration)
    Registration of the 'browser_network_requests' tool which delegates to proxyToolCall.
    server.tool('browser_network_requests', 'Get network requests', {},
      async (args) => {
        const check = requireActivePage();
        if (check) return check;
        return proxyToolCall('browser_network_requests', args);
      });
  • The proxyToolCall function acts as the handler, which forwards the tool request to the underlying MCP client.
    async function proxyToolCall(toolName, args) {
      log(`[proxyToolCall] ${toolName} with args: ${JSON.stringify(args)}`);
      const { client } = await getOrCreateInstance();
      log(`[proxyToolCall] got client for port ${assignedPort}`);
    
      // Update last used
      if (assignedPort && instances.has(assignedPort)) {
        instances.get(assignedPort).lastUsed = Date.now();
      }
    
      try {
        log(`[proxyToolCall] Calling client.callTool...`);
        const result = await client.callTool({ name: toolName, arguments: args || {} });
        log(`[proxyToolCall] Result type: ${typeof result}`);
        log(`[proxyToolCall] Result: ${JSON.stringify(result).slice(0, 500)}`);
    
        // The SDK returns { content: [...], isError?: boolean }
Behavior2/5

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

No annotations provided, so description carries full burden of behavioral disclosure. 'Get' implies read-only but doesn't confirm safety, format of returned data, whether requests are cleared after retrieval, or pagination behavior. Significant gaps for a data retrieval tool.

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

Conciseness3/5

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

Extremely brief (3 words), which prevents verbosity, but underspecified rather than efficiently concise. Single sentence is front-loaded but lacks the content to earn its place effectively.

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?

For a retrieval tool with no output schema, the description fails to explain what data structure is returned, temporal scope, or filtering capabilities. Incomplete given the lack of structured metadata.

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?

Zero parameters present, meeting the baseline of 4. Schema is empty object, so there's nothing to describe.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

States the action (Get) and resource (network requests), which is minimum viable. However, lacks scope specificity (from current page? since navigation? all tabs?) and doesn't differentiate from sibling browser_console_messages or browser_snapshot.

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

Usage Guidelines1/5

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

Provides absolutely no guidance on when to use this tool versus siblings like browser_console_messages or browser_snapshot. No mention of prerequisites (e.g., must navigate first) or temporal constraints.

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/OMGEverdo/browser-pool-mcp'

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