Skip to main content
Glama
Sign In

Proxmint

by com.proxmint
OverviewDiscussionsAdmin

Fetch a page

fetch_url
Read-only

Fetch one web page through a product's proxy, so the request leaves from that product's IPs and targeting: status, final URL (up to 5 redirects), title, and the page as readable text or raw HTML, cut at 50,000 characters. Each call gets a new exit IP. Uses the product's bandwidth for the bytes transferred; binary files are not read.

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": {
      "product": "<product>",
      "url": "<url>"
    },
    "name": "fetch_url"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesThe page to fetch: an http or https URL
formatNotext: readable text, with scripts, styles and tags removed. html: the raw markuptext
countryNoISO 3166 alpha-2 country code, e.g. us. Leave every location field empty to use the targeting saved in the dashboard.
productYesProxy product

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior5/5

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

Goes well past the annotations by disclosing traits an agent needs: a fresh exit IP per call, redirect handling (up to 5), the 50,000-character truncation, that it consumes the product's bandwidth, and that binary files are not read. These are exactly the non-obvious behaviors the readOnly/openWorld hints don't cover.

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?

Front-loads the core action before the colon-separated return/cost details, and every sentence carries information. It is slightly run-on, folding targeting, output fields, and truncation into one dense clause, which costs a point on structure.

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?

With no output schema, the description compensates by enumerating what comes back (status, final URL, title, text or raw HTML) and its limits. Combined with the cost and binary-file notes, an agent has everything needed to call it correctly.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already explains url, format, country, and product with enums and defaults. The description adds only the derived detail (text vs raw HTML, the 50k cut), so the baseline 3 is appropriate.

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 ('Fetch one web page through a product's proxy') and immediately characterizes the mechanism (request leaves from that product's IPs). It is clearly distinguishable from siblings like check_connection or generate_proxies, which do not return page content.

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 explains the 'why' — routing through a chosen product's exit IPs and targeting — which implies when to reach for it. But it never names an alternative (e.g., check_connection first) or states exclusions/prerequisites, so usage is only implied rather than guided.

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

All Proxmint toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources