Skip to main content
Glama
Perplexity Answer Reader MCP Server

Perplexity Answer Reader MCP Server

Ask Perplexity on your own key, with sources

ask_perplexity_with_sources
Read-only

Ask Perplexity questions with your own API key and get each answer with its cited sources, cited domains, brand citation position, and the searches it ran.

Instructions

Give questions and your own Perplexity API key. Returns one row per answer with the answer text, every search result with which ones the answer cites, the cited domains, the searches Perplexity ran, and, if you name a brand, whether the answer names and cites it and at what position. With no key it writes up to 3 free check rows and asks nothing. Pay per event on Apify: 0.01 USD per completed answer, plus your Perplexity bill.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "ask_perplexity_with_sources"
  }
}

Input Schema

NameRequiredDescriptionDefault
brandNoOptional. A brand name, a domain, or both as Name|domain.com. Each row then says whether the answer names the brand and cites its domain, and at what position.
modelNoOptional. An Agent API model ID, for example perplexity/sonar or openai/gpt-5.6-sol. When set, the actor asks that model with Perplexity's web search tool on instead of using an effort level.
effortNoPerplexity's Agent API effort level: fast (default; quick answers with numbered citations), low, medium, or high. Higher levels search more and cost more on your Perplexity bill. Ignored when you name a model.
api_keyNoYour own Perplexity API key, from console.perplexity.ai. It is sent only to api.perplexity.ai and is never stored, logged, or written to a row. With no key, the run checks up to 3 prompts for free and asks nothing.
countryNoOptional. Two letter country code, for example US or DE. Perplexity uses it as the searcher's location.
promptsNoThe questions to ask Perplexity, one per line. Each is sent as written. As text, one prompt per line; a comma does not split a prompt.
competitorsNoOptional. Competitor names or Name|domain.com, one per line. Used for the brand mention rank and the competitors named column.
concurrencyNoHow many prompts to ask at the same time, 1 to 10 (default 3). Lower it if your Perplexity account hits its rate limit.
max_charge_usdNoOptional. The run stops before a charge that would pass this amount. Summary rows are always returned. It does not cap your Perplexity bill.
samples_per_promptNoHow many times to ask each prompt, 1 to 5 (default 1). Answers change between calls, so more samples give a steadier read. Each sample is one Perplexity call and one charged answer.
search_domain_filterNoOptional. Domains for Perplexity's web search to use, or to skip with a leading minus, for example -pinterest.com. Up to 20.
search_recency_filterNoOptional. Limit web search results to the last hour, day, week, month, or year.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.3/5.0
Behavior5/5

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

Beyond the readOnly/openWorld annotations, it discloses that the API key is sent only to api.perplexity.ai and never stored, logged, or written to a row, that no-key runs write up to 3 free check rows and ask nothing, that each sample is one charged Perplexity call, and that max_charge_usd does not cap the Perplexity bill. It also notes concurrency should be lowered on rate limits. These are exactly the operational facts an agent needs before spending a user's money.

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 shape is front-loaded in the first sentence and the cost/key model follows, with almost no filler. The opening sentence is dense with a long enumerated list, which slightly slows parsing but is not wasteful.

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?

With 12 parameters, no output schema, and no annotations covering cost, the description correctly carries the return-row shape, key handling, and billing model. It leaves failure modes (invalid key, quota exhaustion mid-run) largely to inference, which keeps it just short of complete.

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 every parameter is already documented, and the description largely restates that content (brand behavior, no-key fallback). It adds little syntax or format detail beyond the schema, so the baseline of 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?

The description opens with a specific instruction ("Give questions and your own Perplexity API key") and then enumerates exactly what comes back: one row per answer with answer text, search results with citations, cited domains, the searches run, and brand name/citation position. An agent knows precisely what the 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?

It states the operating condition clearly: a user-supplied key for real answers, and no key triggers a free check of up to 3 prompts that asks nothing. It also gives cost context (0.01 USD per completed answer plus the user's Perplexity bill). It stops short of explicit when-not-to-use guidance, though there are no sibling tools to route against.

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