Skip to main content
Glama
perplexity-web-mcp

perplexity-web-mcp

by H1di

perplexity_search

Run Perplexity web searches and return cited answers via your logged-in Pro account, with auto, pro, reasoning, deep research, and academic mode options.

Instructions

Ask Perplexity (web search + answer with citations) using the user's Perplexity Pro subscription.

Args: query: The question or search query. mode: "auto" (fast), "pro" (Pro Search, default), "reasoning", or "deep_research" (slow, thorough). model: Optional raw Perplexity model_preference override (e.g. "pplx_pro"). academic: Search academic sources instead of the general web.

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
modeNopro
modelNo
queryYes
academicNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden, and it does disclose meaningful traits: the call consumes the user's Perplexity Pro subscription (an auth/entitlement prerequisite), returns an answer with citations, and has materially different latency depending on mode. Gaps remain — no mention of rate limits, failure modes, or cost per mode — which keeps it below 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?

The purpose statement is front-loaded in the first sentence, and the Args block is compact, one line per parameter, with zero filler. Nothing repeats structured data verbatim and every clause adds information.

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 4-parameter tool with no annotations and no schema descriptions, the definition covers purpose, the entitlement requirement, and per-parameter meaning, and it needn't explain return values because an output schema exists. The main shortfall is the thin treatment of 'model' and the lack of any failure or rate-limit context.

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

Parameters4/5

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

Schema description coverage is 0%, so the description must compensate, and it largely does: it defines all four parameters including the undocumented 'mode' enum values that the schema leaves as a bare string, plus default behavior and an example for 'model'. The 'model' explanation ('raw Perplexity model_preference override') is terse enough that an agent may not know valid values or how it interacts with 'mode'.

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 names a specific verb-and-resource pair — 'Ask Perplexity (web search + answer with citations)' — and immediately scopes it to 'the user's Perplexity Pro subscription.' An agent knows this is a web-grounded LLM query tool with citations, not a plain search or chat endpoint, and there are no siblings to confuse it with.

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

Usage Guidelines3/5

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

It gives real internal guidance for choosing a mode ('auto (fast)', 'pro' as default, 'reasoning', 'deep_research (slow, thorough)') and flags 'academic' for scholarly sources. It never states when to prefer this tool over another tool or when not to use it, so selection guidance beyond mode choice is left implicit.

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