Skip to main content
Glama

js_recon

Extract API endpoints, URLs, source maps, and possible secrets from a page’s JavaScript to map exposed assets and support authorized reconnaissance.

Instructions

Extract API endpoints, URLs, source maps and potential secrets from a page's JavaScript.

Fetches the page, its script bundles (capped; tracker hosts skipped) and inline scripts, then applies endpoint and secret-pattern regexes. Secret values are masked.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "js_recon"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
max_bytesNo
max_scriptsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.0

TDQS

C2.9/5.0
Behavior2/5

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

No annotations exist, so the description carries the entire behavioral burden. It does useful work here — it states that the page is fetched, that script bundles are capped and tracker hosts skipped, that inline scripts are included, and that secrets are regex-matched and masked in output. That is real behavioral detail that annotations would otherwise supply, and it is the strongest part of the definition. However, it stops short of stating the return shape, error behavior on fetch failure, rate limits, or authentication needs — gaps that a tool with zero annotation coverage should address.

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

Conciseness5/5

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

Three short lines, front-loaded with the extraction verb and outcome, followed by the mechanics. No filler sentences and nothing that could be cut without losing information.

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

Completeness3/5

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

With no output schema, no annotations, and three undocumented parameters, the description should ideally describe the returned structure (e.g. is it a list of endpoints plus a secrets array) and failure modes. It covers the what and some of the how, but leaves the return contract and error behavior unstated. Adequate as a starting point, incomplete for a tool of this complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so all three parameters (url, max_bytes, max_scripts) are undocumented in structured data. The description hints at the existence of caps with 'bundles (capped)' and 'max' concepts, but never explains units, defaults, or how max_bytes/max_scripts alter behavior — an agent cannot tell whether max_bytes is per-script or total. It adds only marginal meaning over the bare schema.

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 opens with a concrete verb and resource: 'Extract API endpoints, URLs, source maps and potential secrets from a page's JavaScript.' It enumerates the four artifact classes returned, so an agent knows exactly what the tool produces. It does not explicitly contrast itself with nearby extraction siblings such as browser_extract or api_discovery, which keeps it at 4 rather than 5.

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

Usage Guidelines2/5

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

There is no statement of when to reach for this tool versus alternatives like browser_extract or background recon tools. Usage is only implied by the passive/JS framing of the output description. An agent must infer the recon-phase context itself.

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