Skip to main content
Glama

Fetch a page through a proxy

fetch_url
Read-only

Load any public web page through a verified free proxy and get readable text. Bypass geo-blocks or site restrictions by fetching from another country.

Instructions

Load a web page through a verified free proxy and return it as readable text.

If a proxy fails, the next one is tried by itself (up to 8), redirects are followed. HTTPS only goes through proxies that passed a verified-TLS test, so the page can't be changed on the way. Local and private addresses are refused, also when a redirect points there. Useful to see a site from another country or when a site blocks this machine. GET only; don't use it for logins or anything with personal data.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesFull http:// or https:// URL of a public site
countryNoTwo-letter code: load the page as seen from this country. Empty = any country.
protocolNoOnly use proxies of this protocolany
raw_htmlNoReturn the HTML as it is instead of readable text
max_charsNoCut the text after this many characters

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYes
viaYesThe proxy that delivered the page
noteYes
textYesReadable text (HTML is turned into plain text unless raw_html is set)
bytesYesSize of the response body
statusYesHTTP status of the target, e.g. 200, 403, 404
final_urlYesAfter redirects
truncatedYesTrue if the text was cut at max_chars
elapsed_msYes
content_typeYes
proxy_countryYesCountry the target saw the request from

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.25.0

TDQS

A4.4/5.0
Behavior5/5

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

Adds substantial behavior beyond the annotations: up to 8 proxies tried in sequence, redirects followed, TLS-verified proxies only for HTTPS, and refusal of local/private addresses even via redirect. These are exactly the operational traits (failure handling, safety boundaries, mutation risk) an agent needs and that readOnlyHint/openWorldHint do not convey.

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-loaded with purpose, then constraints, then usage caveats — every sentence carries information. Slightly dense in the middle sentence about proxy/TLS/redirect handling, but nothing is wasted.

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?

An output schema exists, so return-value detail is not required. The description covers mechanism, safety boundaries, failure behavior, and use/exclusion cases, which is complete for a 5-parameter read tool with one required argument.

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 each parameter is already documented in the schema. The description only loosely maps to parameters ('readable text' implies raw_html, 'from another country' implies country). Baseline 3 applies when the schema does the heavy lifting.

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 plus the mechanism: 'Load a web page through a verified free proxy and return it as readable text.' This clearly distinguishes it from the proxy-management siblings (get_proxies, check_proxies), which do not return page content. An agent can tell what this tool produces without opening the 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?

Gives explicit when-to-use ('see a site from another country or when a site blocks this machine') and when-not ('GET only; don't use it for logins or anything with personal data'). It stops short of naming an alternative tool for those excluded cases, so it falls just below a 5.

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