Skip to main content
Glama
Browser Control MCP Server

Browser Control MCP Server

by lostmind008

network_requests

Capture and retrieve browser network requests, starting monitoring once before reading or clearing captured traffic. Use it to inspect requests per tab.

Instructions

Get captured network requests (must call once to start capturing)

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "network_requests"
  }
}

Input Schema

NameRequiredDescriptionDefault
clearNoClear captured requests (default false)
startNoStart capturing network requests (call once before monitoring)
tabIdNoTab ID (optional)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv3.1.0

TDQS

B3.3/5.0
Behavior3/5

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

With no annotations, the description carries the full burden; it does disclose the non-obvious start-once-before-monitoring behavior, which is valuable. However, it does not say whether results accumulate, whether calling without start returns empty, or that the clear flag irreversibly discards captured data.

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 tight clauses with the retrieval purpose front-loaded and the precondition immediately after. No filler, though the parenthetical is slightly ambiguous about whether start must precede every read or only the first.

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?

No annotations and no output schema mean the description must explain what a returned request entry looks like, whether the list is cumulative, and whether clear is destructive. It covers only the capture-start precondition, leaving the agent guessing about output shape and data-loss risk.

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 description coverage is 100%, so start, clear, and tabId are already documented in the schema and the 3 baseline applies. The description only echoes the 'call once' semantics of start and adds nothing about clear or tabId scoping.

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

Purpose4/5

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

States a specific verb and resource ('Get captured network requests') and adds the operational precondition that capturing must be started. It is reasonably distinguishable from read-only siblings like get_page_content or get_response_body, though it never names them.

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 parenthetical 'must call once to start capturing' implies a two-phase workflow, and the start/clear parameters reinforce it, but the description never states when to prefer this over console_messages or get_response_body, nor any exclusions.

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