Skip to main content
Glama

ie_network

Lists browser HTTP requests captured by a local proxy and XHR instrumentation, filterable by URL, method, status, and since ID, to inspect network activity.

Instructions

List the HTTP requests the browser made, captured by the local recording proxy (and the XHR calls the page instrumentation saw, source page): one line per request, 'id source method status duration_ms size url', oldest first. Filter with url_contains, method and status; pass the last id seen as since_id to page (limit, default 50). Ie_request shows one entry's headers and bodies. HTTPS shows only the tunnel (host, timing). The initial URL of a session and responses served from the browser cache are not seen. Needs no browser call: it works while the page is busy or blocked. IE_CAPTURE=0 turns the proxy off.

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": "ie_network"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoat most this many, oldest first (default 50)
methodNo
statusNo
since_idNoonly entries with a higher id (default 0)
url_containsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: it documents the line format, oldest-first ordering, default page size, the IE_CAPTURE=0 kill switch, and two significant blind spots (HTTPS tunnel-only capture, no cache or initial-URL entries). These are exactly the caveats an agent would otherwise discover only by misinterpreting empty results.

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?

Information is front-loaded: what it lists, then the line format, then filtering and paging, then caveats. It is dense and mostly earns its words, though the parenthetical '(and the XHR calls the page instrumentation saw, source page)' is awkwardly nested and slightly disrupts the opening sentence.

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?

There is no output schema, and the description still specifies the exact return shape and ordering, plus the paging mechanism for consuming it. For a read-only listing tool with five optional parameters, an agent has everything needed to call it and interpret the result.

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?

Schema coverage is only 40%, but the description compensates by explaining every parameter's role: url_contains, method and status as filters, since_id as a forward paging cursor using the last id seen, and limit defaulting to 50. The one gap is matching semantics for url_contains (substring vs. exact) and whether method is case-sensitive.

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 opens with a specific verb and resource ('List the HTTP requests the browser made') and immediately scopes the data source (local recording proxy plus page instrumentation XHR). It also distinguishes itself from the sibling ie_request by explaining that tool shows one entry's headers and bodies.

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

Usage Guidelines4/5

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

It gives clear operating context (works while the page is busy or blocked, needs no browser call) and routes detail lookups to ie_request. It also discloses the important exclusions: HTTPS shows only the tunnel, and the session's initial URL and cache-served responses are invisible. It stops short of naming when to prefer ie_console or ie_network_clear, but the core use case and its boundaries are explicit.

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