Skip to main content
Glama

Inspect Web Network Capture

inspect_web_network_capture
Idempotent

Inspects local HAR, mitmproxy, Fiddler SAZ, or qlog captures offline to decode records and return ordinals, byte ranges, preserved fields, and exact binary data without contacting recorded URLs.

Instructions

Request detail summary for capture identity and counts; then page retained records with inspect_analysis_view kind capture (preview or complete), avoiding repeated decoding. Default detail complete preserves existing inline delivery. Inspect retained local HAR 1.2, native mitmproxy, Fiddler SAZ or aioquic 1.5.0 JSON qlog 0.3 events without contacting recorded URLs. Returns original ordinals, pointers/byte ranges/archive member names, preserved producer fields, precise numeric representations and exact exposed binary bytes inline. Excludes known transport credentials and explicitly marked values. Decodes every record before optional ordinal selection; malformed or oversized captures return no partial success. Duplicate JSON members are invalid; prototype-named members such as proto are preserved as ordinary own JSON members without prototype mutation. Qlog reports trace-scoped STREAM interval unions and endpoint loss declarations; it does not recover bodies, prove network loss or correlate PCAP. Other qlog layouts are unsupported. Uses pinned upstream parsers, owned temporary files and bounded offline processes. SAZ preserves HTTP fields, XML metadata and encoded body/message bytes without replay or HAR conversion; encrypted archives are unsupported. Native mitmproxy requires caller-supplied mitmdump 12.2.3 on Linux. Browser transaction IDs, runtime attribution and original bytes of HAR Unicode text remain unknown.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "format": "qlog",
      "capture_path": "/captures/origin.qlog",
      "record_ordinals": [
        0,
        2
      ]
    },
    "name": "inspect_web_network_capture"
  }
}

Input Schema

NameRequiredDescriptionDefault
detailNofull/complete returns the complete analysis Evidence inline. summary retains that complete Evidence in this session and returns its inspect_analysis_view summary; inspect pages, items or facets through normalized_result.parent_evidence_id.
formatYesDeclared input artifact format.
capture_pathYesAbsolute local HAR, mitmproxy, Fiddler SAZ or aioquic qlog capture path.
record_ordinalsNoZero-based producer record ordinals, in caller-selected order. Omit to inspect every record.
sensitive_valuesNoLiteral text excluded from capture payloads, byte/numeric projections, producer coordinates, artifact paths/digests and diagnostic text. Declaration strings are never persisted in Evidence parameters. Canonical contract keys, enums and provider identities remain intact.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior5/5

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

Beyond the annotations, the description discloses extensive behavior: it never contacts recorded URLs, runs bounded offline processes, uses owned temporary files, excludes credentials and marked values, decodes every record before optional ordinal selection, and fails without partial success for malformed or oversized captures. It also documents prototype-safety handling, qlog limitations, SAZ preservation rules, and mitmproxy version/platform requirements. This is unusually rich behavioral context for a complex inspection 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?

The description is information-dense with little filler, but it is a long run-on block that leads with parameter workflow before stating the tool's core purpose. Several sentences pack multiple independent constraints together, making it harder to scan than it could be. It is not verbose in the sense of empty wording, but it is structurally dense and poorly front-loaded.

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?

For a complex offline capture-inspection tool with no output schema, it covers supported formats, offline guarantees, credential exclusions, failure behavior, qlog limitations, and mitmproxy requirements thoroughly. It also describes the shape of returned data in general terms such as ordinals, byte ranges, archive members, producer fields, and binary bytes. Some terms like 'Evidence' remain only loosely defined, but overall it is more complete than most definitions.

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 description coverage is already 100%, so the baseline is 3. The description still adds useful parameter-specific meaning: detail=summary retains complete evidence for later paging through inspect_analysis_view, record_ordinals are applied only after all records are decoded, and sensitive_values affect payload projections, paths, digests, and diagnostics. It does not add much about the format enum beyond naming supported formats, keeping it below 5.

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?

The description states a specific verb and resource: inspecting retained local HAR 1.2, mitmproxy, Fiddler SAZ, and aioquic qlog 0.3 captures. It distinguishes itself from broader packet-capture tools by explicitly saying it does not correlate PCAP and that qlog layouts other than aioquic are unsupported. The opening clause about detail summaries delays the core purpose, preventing a 5.

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 a clear workflow: request detail summary first, then page records via inspect_analysis_view kind capture, and use record_ordinals only when selecting specific records. It also implies the tool is for local capture formats rather than live or PCAP analysis. It does not explicitly route agents to siblings such as inspect_packet_capture or compare_web_captures when those are better fits.

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

Deploy Server

Other Tools