perplexity

A skill for searching the web with Perplexity through a scraper server. It supports ordinary lookups and more involved research that combines sources and provides citations.

In plain words
What is it for?
Use it for current-events research, factual web lookups, source-backed answers, comparisons, and questions requiring information from multiple online sources.
Why use it?
It helps answer questions that need current web information or several sources instead of relying only on existing knowledge. The reasoning option is intended for comparisons and multi-step analysis.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/cotdp/scraper-mcp/perplexity
Any agent
npx skills add cotdp/scraper-mcp --skill perplexity
Clone the repo
git clone --depth 1 https://github.com/cotdp/scraper-mcp

Made for: Claude Code, Codex.

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,341 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00057 $0.01341
Opus 5 $0.00028 $0.00671
Sonnet 5 $0.00011 $0.00268
Haiku 4.5 $0.00006 $0.00134

Measured 2d ago against content hash 176719bc10bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

perplexity scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/perplexity/SKILL.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Perplexity AI Skill

AI-powered web search and reasoning capabilities via the scraper MCP server.

When to Use This Skill

  • Searching the web with AI-synthesized answers
  • Research tasks requiring multiple sources with citations
  • Complex reasoning and multi-step analysis
  • Questions about current events or real-time information
  • Comparing options or analyzing trade-offs

Available Tools

Tool Model Best For
mcp__scraper__perplexity sonar General queries, quick searches, factual lookups
mcp__scraper__perplexity_reason sonar-reasoning-pro Complex analysis, comparisons, multi-step reasoning

Tool Usage

1. General Web Search

For straightforward queries and information lookup:

mcp__scraper__perplexity(
    messages=[
        {"role": "user", "content": "What are the latest features in Next.js 15?"}
    ],
    model="sonar",
    temperature=0.3,
    max_tokens=4000
)

Response includes:

  • content: AI-synthesized answer with citation markers [1], [2], etc.
  • citations: Array of source URLs
  • model: Model used
  • usage: Token statistics

2. Complex Reasoning

For analytical queries requiring deep thinking:

mcp__scraper__perplexity_reason(
    query="Compare React Server Components vs traditional SSR approaches. Consider performance, developer experience, and migration complexity.",
    temperature=0.3,
    max_tokens=4000
)

Use cases:

  • Technology comparisons
  • Architecture decisions
  • Trade-off analysis
  • Multi-factor evaluations

Parameters

Parameter Type Default Description
messages array required Conversation history (perplexity only)
query string required Question to reason about (perplexity_reason only)
model string "sonar" "sonar" or "sonar-pro"
temperature number 0.3 Creativity 0-2 (lower = more focused)
max_tokens integer 4000 Maximum response length

Read the full file on GitHub · 202 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 202 lines · 57 tokens per session scan A 176719bc10bd

Subscribe to this mod's changes

perplexity is a skill published in the GitHub repository cotdp/scraper-mcp (7 stars, last pushed 3mo ago), licensed MIT. It adds 57 tokens to every session and 1,341 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.