Skip to main content
Glama

Find a working proxy

find_proxy

Find a working free proxy when a direct request is geo-blocked or fails. Tests candidates against your target URL and returns a live proxy plus backups, filterable by country or protocol.

Instructions

Finds a live, validated free proxy, optionally filtered by country and/or protocol. Tests a batch of candidates concurrently against a target URL and returns the fastest one that actually works, plus a few backups. Use this when a direct request/curl is geo-blocked or otherwise failing and you need a working proxy to route through.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
countryNoISO 3166-1 alpha-2 country code (e.g. "FR") or full country name (e.g. "France"). Omit for any country.
testUrlNoURL to validate candidates against. Defaults to a generic IP-echo endpoint; pass the site you actually need to reach (e.g. the one your curl just failed against) for a more relevant check.
protocolNoProxy protocol to filter by, or "any" for no filter.
timeoutMsNoPer-proxy check timeout in ms. Default 4000.
concurrencyNoMax concurrent checks. Default 10.
forceRefreshNoBypass the cached proxy list and re-fetch all sources.
maxCandidatesNoMax candidates to live-test. Default 25.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.2

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does reasonably well: it discloses concurrent batch testing against a target URL, that it returns the fastest working proxy plus backups, and (via forceRefresh/'cached proxy list') that a cache exists. It omits rate limits, timeout/failure behavior on no match, and whether network egress occurs, keeping it from a 5.

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 sentences, front-loaded with the core action, followed by mechanics, then usage condition. Every sentence adds distinct value with no redundancy.

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 7-param tool with no output schema, the description covers purpose, selection behavior, and return shape ('fastest one that actually works, plus a few backups'). It lacks guidance on no-match outcomes and the cache's behavioral implications, minor gaps that keep it from 5.

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 documents all 7 parameters with defaults and bounds. The description adds no syntax or format detail beyond what the schema provides, so baseline 3 applies.

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+resource ('Finds a live, validated free proxy') with scope ('optionally filtered by country and/or protocol') and contrasts implicitly with siblings like check_proxy or list_proxies by emphasizing validated-and-working selection. An agent can distinguish this as the search-and-validate tool.

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 concrete when-to-use guidance: 'when a direct request/curl is geo-blocked or otherwise failing and you need a working proxy to route through.' It does not name sibling alternatives (check_proxy vs list_proxies) to route away, so it falls short of 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