Skip to main content
Glama
Sign In
SoftGlaze Browser MCP

SoftGlaze Browser MCP

by softglazee
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Profile health and CAPTCHA risk

profile_health
Read-onlyIdempotent

Checks a browser profile's CAPTCHA risk from proxy health, IP type, timezone/location mismatch, WebRTC, cookies, history, and fingerprint coherence, with fixes; can test the proxy live.

Instructions

Explains how likely a profile is to get CAPTCHAs and why: proxy health and blocklist, datacenter or home IP, shared proxy, timezone/language/location vs the proxy, WebRTC, third-party cookies, browsing history and fingerprint coherence, each with its fix. live: true also tests the proxy now and compares its exit country and timezone with the profile. Changes nothing.

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": {
      "id": "<id>"
    },
    "name": "profile_health"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesProfile id.
liveNoAlso test the proxy now (takes up to 30 seconds).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety and network-touching profile is known; the description adds that live=true performs an active proxy test of up to 30 seconds and compares exit country/timezone against the profile — real behavioral context beyond the annotations. It reinforces 'Changes nothing' (largely redundant with readOnlyHint) but does not explain failure modes, e.g. what happens with no proxy assigned or if the live test times out.

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?

Purpose is front-loaded in the opening clause, followed by the factor list and then the live-mode caveat; no filler sentences. The middle sentence is a long comma-chain that is dense but still scannable, and every clause contributes a distinct checked factor.

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?

With no output schema, the description usefully substitutes by enumerating what the diagnosis covers ('each with its fix'), so an agent knows what comes back. The 30-second latency caveat for live mode is also essential operational context for a tool that may block. Minor gap: no indication of result format or whether findings are ranked by severity.

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

Parameters1/5

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

placeholder

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 outcome — 'Explains how likely a profile is to get CAPTCHAs and why' — then enumerates the exact factors examined (proxy health/blocklist, IP type, shared proxy, timezone/language/location vs proxy, WebRTC, cookies, history, fingerprint coherence). This makes it clearly a per-profile CAPTCHA-risk diagnostic, distinguishable from the narrower get_proxy_health sibling.

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 description gives conditional guidance for the optional parameter ('live: true also tests the proxy now...'), which implies when the slower path is warranted. However, it never states when to prefer this tool over siblings like get_proxy_health or check_proxy, nor any prerequisite such as the profile needing to exist or a proxy being assigned. Usage is implied rather than directed.

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