Skip to main content
Glama
Perplexity Answer Reader MCP Server

Perplexity Answer Reader MCP Server

README.md
# Perplexity Answer Reader MCP Server

[![npm version](https://img.shields.io/npm/v/@mambalabsdev/mcp-perplexity-answer-reader)](https://www.npmjs.com/package/@mambalabsdev/mcp-perplexity-answer-reader) [![license](https://img.shields.io/github/license/mambalabsdev/mcp-perplexity-answer-reader)](https://github.com/mambalabsdev/mcp-perplexity-answer-reader/blob/main/LICENSE)

An MCP server for the Mamba Labs Perplexity Answer Reader actor on Apify. Perplexity answers and their cited sources, on your own key.

## What's Inside

- [What it does](#what-it-does)
- [Quick start](#quick-start)
- [Prerequisites](#prerequisites)
- [Example prompts](#example-prompts)
- [Tool](#tool)
- [Inputs](#inputs)
- [Pricing](#pricing)
- [Full actor documentation](#full-actor-documentation)
- [License](#license)

## What it does

Give questions and your own Perplexity API key. The actor asks each question through Perplexity's Agent API with web search on and returns one row per answer: the answer text, every source Perplexity found with which ones the answer cites, the cited domains in order, and the searches it ran. Name a brand and each row also says whether the answer names it, cites its domain, and at what position. You pay Perplexity directly and this actor per completed answer.

All of the work runs on Apify. This package is a thin client that starts the actor run, waits for it, and hands back the dataset rows.

## Quick start

You need Node.js 18 or newer and an Apify account with an API token.

Add this to your Claude Desktop config (`claude_desktop_config.json`), Cursor, or any MCP client:

```json
{
  "mcpServers": {
    "mamba-perplexity-answer-reader": {
      "command": "npx",
      "args": [
        "-y",
        "@mambalabsdev/mcp-perplexity-answer-reader"
      ],
      "env": {
        "APIFY_TOKEN": "your-apify-token"
      }
    }
  }
}
```

Restart the client. The `ask_perplexity_with_sources` tool appears.

## Prerequisites

- Node.js 18 or newer.
- An Apify API token from [console.apify.com/account/integrations](https://console.apify.com/account/integrations), set as `APIFY_TOKEN`. The server lists its tool without a token; a call needs one.

## Example prompts

- "Ask Perplexity these 10 buyer questions on my key and tell me which answers cite hubspot.com."
- "Ask the same question 5 times and list every domain Perplexity cites."
- "What sources does Perplexity use to answer questions about project management tools?"

## Tool

`ask_perplexity_with_sources`. One tool. Example arguments:

```json
{
  "prompts": [
    "What is the best CRM for a 10 person sales team?"
  ],
  "brand": "HubSpot|hubspot.com"
}
```

## Inputs

Every buyer facing input of the actor. Omitted inputs take the actor's own defaults.

| Input | Type | Required | Description |
|---|---|---|---|
| `prompts` | array | no | The 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. |
| `api_key` | string | no | Your 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. |
| `effort` | string | no | Perplexity'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. |
| `model` | string | no | Optional. 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. |
| `brand` | string | no | Optional. 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. |
| `competitors` | array | no | Optional. Competitor names or Name/domain.com, one per line. Used for the brand mention rank and the competitors named column. |
| `samples_per_prompt` | number | no | How 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_filter` | array | no | Optional. Domains for Perplexity's web search to use, or to skip with a leading minus, for example -pinterest.com. Up to 20. |
| `search_recency_filter` | string | no | Optional. Limit web search results to the last hour, day, week, month, or year. |
| `country` | string | no | Optional. Two letter country code, for example US or DE. Perplexity uses it as the searcher's location. |
| `concurrency` | number | no | How 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_usd` | string | no | Optional. The run stops before a charge that would pass this amount. Summary rows are always returned. It does not cap your Perplexity bill. |

## Pricing

Pay per event on Apify, billed to your Apify account. Prices in USD.

| Event | Free plan | Bronze | Silver | Gold |
|---|---|---|---|---|
| `answer-row`, one completed answer with its sources | $0.01 | $0.0095 | $0.009 | $0.0085 |
| `apify-actor-start`, per run start | $0.002 | $0.002 | $0.002 | $0.002 |

Refused, failed, and unfinished answers, check rows with no key, and refused input are free. Mamba Labs pays the platform costs of the run. Mamba Labs pays the platform costs of the run, Apify proxy traffic included.

## Full actor documentation

[apify.com/mambalabs/perplexity-answer-reader](https://apify.com/mambalabs/perplexity-answer-reader)

## License

MIT. See [LICENSE](LICENSE).

TDQS

A4.1/5.0

Scored across 1 tool

Disambiguation4/5

With only one tool there is no risk of misselecting between alternatives, so the surface is trivially unambiguous. However, the single tool multiplexes several distinct modes (paid answer, free check rows with no key, optional brand-mention analysis), which blurs what the tool actually does in any given call.

Naming Consistency4/5

The name ask_perplexity_with_sources is clear snake_case verb_noun form and, being the only tool, cannot conflict with anything. The 'with_sources' suffix describes the return shape rather than the action, which makes the name slightly less action-oriented than ideal.

Tool Count3/5

A single tool is defensible for a narrow Perplexity-wrapper service, and it is not padded with redundant endpoints. Still, one tool carrying answer generation, source/citation extraction, search-query reporting, and brand-position checking feels thin and overloaded for the scope implied by the description.

Completeness3/5

The core operation — ask a question, get answer plus sources and citations — is fully covered, including a no-key trial path. Gaps remain: no way to continue a conversation or ask follow-ups, no batch/multi-question call, and no retrieval of earlier answers, which agents doing iterative research would need.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues