Skip to main content
Glama

perplexity_chat: GET /

hasdata_perplexity_chat_getPerplexityAnswer

Get Perplexity Answer

Sends a question to Perplexity anonymously and returns the answer as markdown text, plus every web page Perplexity cited in sources with its domain, title, snippet, publishedDate and citation number, the follow-up questions in relatedQuestions, a link to the thread on perplexity.ai in url, the model that answered and the country the answer was served from. Perplexity searches the web for every question, so usedWebSearch is normally true and answers come with sources rather than from the model alone. The language of the answer follows the question — write it in the language you want back, or ask for one in it. Set the frame of reference for words like "today" with timezone. Each request is a fresh thread with no memory of earlier ones. Use to answer questions with cited sources, to ground an agent or RAG pipeline in live web results, to summarise a topic with the pages behind it, or to build datasets of answers and their citations.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
promptYesThe question to send to Perplexity, up to 4000 characters. The question also decides the language of the answer — write it in the language you want back, or ask for one explicitly ("Antworte auf Deutsch").
timezoneNoIANA time zone name, for example `America/Chicago` or `Europe/Berlin`. It sets what Perplexity treats as the current date and time, which matters for questions that say "today", "this week" or "latest".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so well: it discloses that requests are anonymous, that each request is a fresh thread with no memory, that `usedWebSearch` is normally true so answers hinge on live sources, and that answer language follows the question language. These are exactly the behavioral traits an agent needs before calling.

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?

The return-value enumeration up front is dense but earns its place given no output schema exists. A few clauses repeat points already in the schema (language, timezone), costing a little tightness.

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 fully enumerates the returned fields and their meaning, and explains web-search behavior, thread isolation, and language handling. An agent has everything needed to call and interpret it.

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 both `prompt` and `timezone` are already fully documented in the schema with the same language-follows-question and IANA-format details. The description restates rather than extends that, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb (sends a question) and resource (Perplexity answer service), and states exactly what comes back: an `answer` plus `sources`, `relatedQuestions`, `url`, `model` and `country`. It is clearly distinct from data-scraping siblings, though it never contrasts itself with the near-twin hasdata_chatgpt_chat_getChatgptAnswer.

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?

Four concrete scenarios are listed (answering with citations, grounding a RAG pipeline, topic summarisation with sources, dataset building). These give a strong sense of when to reach for it, but there is no explicit when-not guidance or routing to the ChatGPT sibling.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.