Skip to main content
Glama

browser_network_requests

Read-onlyIdempotent

Retrieve recorded network requests for a browser tab to inspect URLs, statuses, types, sizes, and errors, with filters for method, status, resource type, and failures.

Instructions

Network requests recorded for the tab (ring buffer of 500), most recent last: url, method, status, type (Document, Fetch, XHR, Script...), mimeType, size (bytes received), duration_ms, state, failed and errorText, request_id (for browser_network_response).

Filters: filter (URL fragment or "/regex/"), method, status (200, "4xx", "400-499"), resource_type, failed_only. include_headers=True adds headers; Cookie, Set-Cookie, Authorization and any header whose name suggests a token, key, session, signature or password are always masked, as are sensitive URL parameters (access_token, code, key, signature, X-Amz-*...). Recording runs while the debugger is attached: browser_network_record keeps it attached for a bounded time.

Input Schema

NameRequiredDescriptionDefault
limitNo
filterNo
methodNo
statusNo
tab_idYesYour tab's id (from browser_new_tab, or a tab adopted with browser_adopt_tab).
failed_onlyNo
resource_typeNo
include_headersNo

Output Schema

NameRequiredDescriptionDefault
dataYes
statusYes
warningNoEmergency stop hotkey not held, or similar notice
untrusted_noteNoPage text that looks like instructions aimed at an AI

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changedv2.31.6
    • addedOutput schema / $defs
      Added value: +{
      +  "NetworkLog": {
      +    "additionalProperties": true,
      +    "properties": {
      +      "buffer_size": {
      +        "type": "integer"
      +      },
      +      "buffered": {
      +        "type": "integer"
      +      },
      +      "count": {
      +        "type": "integer"
      +      },
      +      "dialog": {
      +        "$ref": "#/$defs/PageDialog"
      +      },
      +      "dialogOpened": {
      +        "type": "boolean"
      +      },
      +      "message": {
      +        "type": "string"
      +      },
      +      "note": {
      +        "type": "string"
      +      },
      +      "pendingDialogs": {
      +        "items": {
      +          "$ref": "#/$defs/PageDialog"
      +        },
      +        "type": "array"
      +      },
      +      "recording_since": {
      +        "type": "string"
      +      },
      +      "recording_until": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ]
      +      },
      +      "requests": {
      +        "items": {
      +          "$ref": "#/$defs/NetworkRequest"
      +        },
      +        "type": "array"
      +      },
      +      "total_matching": {
      +        "type": "integer"
      +      }
      +    },
      +    "title": "NetworkLog",
      +    "type": "object"
      +  },
      +  "NetworkRequest": {
      +    "additionalProperties": true,
      +    "description": "Recorded request. Secret URL parameters and secret headers (cookies, authorization, tokens...) are masked.",
      +    "properties": {
      +      "blockedReason": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ]
      +      },
      +      "canceled": {
      +        "type": "boolean"
      +      },
      +      "duration_ms": {
      +        "anyOf": [
      +          {
      +            "type": "number"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ]
      +      },
      +      "errorText": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ]
      +      },
      +      "failed": {
      +        "type": "boolean"
      +      },
      +      "frame": {
      +        "type": "string"
      +      },
      +      "fromCache": {
      +        "type": "boolean"
      +      },
      +      "method": {
      +        "type": "string"
      +      },
      +      "mimeType": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ]
      +      },
      +      "redirectedFrom": {
      +        "type": "string"
      +      },
      +      "redirectedTo": {
      +        "type": "string"
      +      },
      +      "requestHeaders": {
      +        "anyOf": [
      +          {
      +            "additionalProperties": true,
      +            "type": "object"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ]
      +      },
      +      "request_id": {
      +        "type": "string"
      +      },
      +      "responseHeaders": {
      +        "anyOf": [
      +          {
      +            "additionalProperties": true,
      +            "type": "object"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ]
      +      },
      +      "size": {
      +        "anyOf": [
      +          {
      +            "type": "number"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ]
      +      },
      +      "startedAt": {
      +        "type": "string"
      +      },
      +      "state": {
      +        "type": "string"
      +      },
      +      "status": {
      +        "anyOf": [
      +          {
      +            "type": "integer"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ]
      +      },
      +      "statusText": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ]
      +      },
      +      "type": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ]
      +      },
      +      "url": {
      +        "type": "string"
      +      }
      +    },
      +    "title": "NetworkRequest",
      +    "type": "object"
      +  },
      +  "PageDialog": {
      +    "additionalProperties": true,
      +    "description": "Dialog opened by the page (never accepted by the agent: browser_handle_dialog).",
      +    "properties": {
      +      "defaultPrompt": {
      +        "type": "string"
      +      },
      +      "message": {
      +        "type": "string"
      +      },
      +      "tabId": {
      +        "type": "integer"
      +      },
      +      "type": {
      +        "type": "string"
      +      },
      +      "url": {
      +        "type": "string"
      +      }
      +    },
      +    "title": "PageDialog",
      +    "type": "object"
      +  }
      +}
    • addedOutput schema / additionalProperties
      Added value: +true
    • addedOutput schema / description
      Added value: +"Network requests recorded for the tab."
    • addedOutput schema / properties / data
      Added value: +{
      +  "$ref": "#/$defs/NetworkLog"
      +}
    • removedOutput schema / properties / result
      Removed value: -{
      -  "title": "Result",
      -  "type": "string"
      -}
    • addedOutput schema / properties / status
      Added value: +{
      +  "const": "success",
      +  "type": "string"
      +}
    • addedOutput schema / properties / untrusted_note
      Added value: +{
      +  "description": "Page text that looks like instructions aimed at an AI",
      +  "type": "string"
      +}
    • addedOutput schema / properties / warning
      Added value: +{
      +  "description": "Emergency stop hotkey not held, or similar notice",
      +  "type": "string"
      +}
    • changedOutput schema / required
      Previous value: -[
      -  "result"
      -]New value: +[
      +  "status",
      +  "data"
      +]
    • changedOutput schema / title
      Previous value: -"browser_network_requestsOutput"New value: +"NetworkAnswer"
  2. First observedv0.1.0

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds substantive traits beyond them: a 500-entry ring buffer, most-recent-last ordering, mandatory masking of Cookie/Set-Cookie/Authorization/token-like headers and sensitive URL params, and the debugger-attachment requirement for recording. These are exactly the behaviors an agent would otherwise have to discover by trial.

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?

Dense but front-loaded: purpose and buffer semantics come first, then return fields, then filters, then the security/masking note. Almost every clause earns its place, though the run-on field list and the trailing debugger note make it slightly heavy to scan.

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

Completeness4/5

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

An output schema exists, so return values needn't be detailed further, and the description covers the non-obvious recording lifecycle and masking behavior. Only the unexplained `limit` and the absence of guidance on buffer overflow (what happens beyond 500 entries) leave minor gaps.

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?

With only 13% schema description coverage, the description carries the burden well: it gives filter syntax (URL fragment or "/regex/"), status grammar (200, "4xx", "400-499"), and spells out side effects of include_headers (masking). The one gap is `limit`, which is never explained despite driving the return size.

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?

States a specific verb and resource — network requests recorded for a tab — and immediately enumerates the returned fields (url, method, status, type, mimeType, size, duration_ms, state, failed, errorText, request_id). The request_id mention explicitly ties it to the sibling browser_network_response, so an agent can distinguish the two without opening a schema.

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?

Explains the filtering axes and the critical precondition that recording only happens while the debugger is attached, pointing at browser_network_record to keep it attached and browser_network_response to fetch a body. No explicit 'when not to use' or alternative listing tool is given, but the context is clear enough.

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