Skip to main content
Glama
Sign In
ProxyAPI-Perplexity

ProxyAPI-Perplexity

by spolperim-lab
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Поиск в интернете (Perplexity)

perplexity_search

Searches the web via Perplexity and returns an answer with source links and request cost, with quick, pro, or reasoning modes for fresh, verifiable information.

Instructions

Ищет ответ в интернете через Perplexity и возвращает текст со ссылками на источники и стоимость запроса. Режимы: quick — быстрый факт, новость, проверка «так ли это» (perplexity/sonar, обычно меньше 1 ₽); pro — нужно больше источников и подробностей, сравнение вариантов (perplexity/sonar-pro, ~2–10 ₽); reason — нужен вывод из нескольких источников, «почему», «что выбрать» (perplexity/sonar-reasoning-pro, ~2–10 ₽). Для большого обзора темы используй perplexity_research. По умолчанию quick. Используй, когда нужна свежая или проверяемая информация из сети, а не общие знания. ВАЖНО: каждый вызов платный (списывается с баланса ProxyAPI пользователя). Перед вызовом обязательно спроси разрешение, показав вопрос, режим и примерную цену, и вызывай только после явного согласия. В конце ответа инструмент сам пишет фактическую стоимость — передай её пользователю.

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": {
      "query": "<query>"
    },
    "name": "perplexity_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoРежим поискаquick
queryYesВопрос для поиска — лучше полной фразой и с контекстом
domainsNoИскать только на этих сайтах ["habr.com"] или исключить сайты через минус ["-pinterest.com"]. Не смешивать
recencyNoТолько свежие источники: за последний час/день/неделю/месяц/год
academicNoИскать по научным публикациям (с ним фильтры по датам не работают)
languagesNoЯзыки источников, коды ISO 639-1: ["ru", "en"]
after_dateNoТолько опубликованное после даты, формат ММ/ДД/ГГГГ
max_tokensNoЛимит длины ответа (по умолчанию зависит от режима)
before_dateNoТолько опубликованное до даты, формат ММ/ДД/ГГГГ

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations only say openWorldHint=true, readOnlyHint=false, idempotentHint=false; the description adds the crucial behavior annotations miss — every call costs real money from the user's ProxyAPI balance, with per-mode price bands, plus the fact that the tool appends its actual cost to the answer. It stops short of describing latency or failure/refund behavior, so it is not 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.

Conciseness4/5

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

Front-loaded with purpose then modes then the cost/permission gate; nearly every clause carries information (mode→model→price→use case). It is long, but the length is driven by three modes plus a mandatory consent rule rather than padding.

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?

Nine parameters and no output schema, yet the description covers return content (text with source links plus stated cost), default mode, and the consent workflow. Minor gaps remain: nothing about how domains/recency interact with the reason/pro modes or what happens when the balance is insufficient.

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

Parameters5/5

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

Schema coverage is 100%, so 3 would be the baseline, but the description genuinely enriches the most important parameter by explaining what each mode enum value is for and roughly what it costs. That is meaning an agent cannot derive from the schema's bare 'Режим поиска'.

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 ('Ищет ответ в интернете через Perplexity'), spells out what is returned (текст со ссылками и стоимостью), and enumerates the three modes with their underlying models. It explicitly distinguishes itself from perplexity_research, so an agent can separate the two without opening a schema.

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

Usage Guidelines5/5

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

Gives concrete when-to-use criteria per mode (quick = быстрый факт/проверка, pro = сравнение вариантов, reason = вывод из нескольких источников), names the alternative for broad surveys, states the default, and adds a hard precondition: ask the user's permission with question, mode and price before calling.

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