What is perplexity-tools?

Perfect for AI Analysis Agents needing efficient Perplexity AI query execution via Python CLI. perplexity-tools is a specialized AI query execution tool that utilizes Python CLI and auto-injects API keys via 1Password, supporting various Sonar family models.

How do I install perplexity-tools?

Run the command: npx killer-skills add bsamiee/Parametric_Portal/perplexity-tools. It works with Cursor, Windsurf, VS Code, Claude Code, and 15+ other IDEs.

What are the use cases for perplexity-tools?

Key use cases include: Executing Perplexity AI queries for optimized response quality, Utilizing sonar family models for lightweight search, deeper retrieval, and real-time reasoning, Automating API key management via 1Password for seamless query execution.

Which IDEs are compatible with perplexity-tools?

This skill is compatible with Cursor, Windsurf, VS Code, Claude Code, GitHub Copilot, JetBrains, Cline, Roo Code, and many more. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for perplexity-tools?

Requires Perplexity AI API key. Dependent on 1Password for API key auto-injection. Limited to Python CLI execution.

[H1][PERPLEXITY-TOOLS]

Name: perplexity-tools
Availability: InStock
Rating: 2.1 (1 reviews)
Author: bsamiee

Dictum: Specialized models optimize response quality.

<br>

Execute Perplexity AI queries via Python CLI. API key auto-injected via 1Password.

[IMPORTANT] Sonar family models (Feb 2026): sonar (lightweight search), sonar-pro (deeper retrieval, 2x more results), sonar-reasoning (real-time reasoning), sonar-reasoning-pro (DeepSeek-R1, visible reasoning), sonar-deep-research (long-form reports). Citation tokens no longer billed for sonar/sonar-pro.

[1][COMMANDS]

[CMD]	[ARGS]	[MODEL]
ask	`<query>`	sonar
pro	`<query>`	sonar-pro
research	`<query> [strip]`	sonar-deep-research
reason	`<query> [strip]`	sonar-reasoning-pro
search	`<query> [max] [country]`	sonar

[2][USAGE]

bash
1# Quick question with citations (lightweight)
2uv run .claude/skills/perplexity-tools/scripts/perplexity.py ask "What is Effect-TS?"
3
4# Pro question with deeper retrieval
5uv run .claude/skills/perplexity-tools/scripts/perplexity.py pro "Compare Vite 7 vs Turbopack bundling strategies"
6
7# Deep research (10min timeout)
8uv run .claude/skills/perplexity-tools/scripts/perplexity.py research "React 19 new features"
9
10# Deep research, strip thinking tags
11uv run .claude/skills/perplexity-tools/scripts/perplexity.py research "Vite 7 migration" strip
12
13# Reasoning task
14uv run .claude/skills/perplexity-tools/scripts/perplexity.py reason "Compare Effect vs RxJS"
15
16# Web search with max results
17uv run .claude/skills/perplexity-tools/scripts/perplexity.py search "Nx 22 features" 5

[3][ARGUMENTS]

ask: <query>

query — Question to ask (required)
Model: sonar (fast, lightweight search)

pro: <query>

query — Question requiring deeper retrieval (required)
Model: sonar-pro (enhanced search, 2x results)

research: <query> [strip]

query — Research topic (required)
strip — Pass strip to remove <think> tags from response
Model: sonar-deep-research (long-form, source-dense reports)

reason: <query> [strip]

query — Reasoning problem (required)
strip — Pass strip to remove <think> tags from response
Model: sonar-reasoning-pro (DeepSeek-R1, visible chain-of-thought)

search: <query> [max] [country]

query — Search query (required)
max — Max results (default: 10)
country — Country code to focus results (e.g., US, GB)

[4][OUTPUT]

Commands return: {"status": "success|error", ...}.

[INDEX]	[CMD]	[RESPONSE]
[1]	`ask`	`{query, response, citations[]}`
[2]	`pro`	`{query, response, citations[]}`
[3]	`research`	`{query, response, citations[]}`
[4]	`reason`	`{query, response}`
[5]	`search`	`{query, results[]}`

[5][ENVIRONMENT]

[VAR]	[REQUIRED]	[DESCRIPTION]
`PERPLEXITY_API_KEY`	Yes	Perplexity API key (1Password injected)

[6][ERROR_HANDLING]

HTTP errors print [ERROR] <status>: <body> and exit 1
Rate limit (429): print retry guidance and exit 1
research command uses 10-minute timeout; long-running queries may time out
reason output includes <think> tags by default; pass strip to remove

perplexity-tools — how to use perplexity-tools how to use perplexity-tools, perplexity-tools setup guide, perplexity-tools alternative, perplexity-tools vs sonar, perplexity-tools install, what is perplexity-tools, perplexity-tools python cli, sonar family models, perplexity ai queries

# Core Topics

↓ Quality Score

Agent Capability Analysis

Ideal Agent Persona

Core Value

↓ Capabilities Granted for perplexity-tools MCP Server

! Prerequisites & Limits

# Tags

[H1][PERPLEXITY-TOOLS]

[1][COMMANDS]

[2][USAGE]

[3][ARGUMENTS]

[4][OUTPUT]

[5][ENVIRONMENT]

[6][ERROR_HANDLING]

Related Skills

Looking for an alternative to perplexity-tools or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

widget-generator

chat-sdk

zustand

data-fetching

perplexity-tools — how to use perplexity-tools how to use perplexity-tools, perplexity-tools setup guide, perplexity-tools alternative, perplexity-tools vs sonar, perplexity-tools install, what is perplexity-tools, perplexity-tools python cli, sonar family models, perplexity ai queries

About this Skill

Features

# Core Topics

↓ Quality Score

Agent Capability Analysis

Ideal Agent Persona

Core Value

↓ Capabilities Granted for perplexity-tools MCP Server

! Prerequisites & Limits

# Tags

[H1][PERPLEXITY-TOOLS]

[1][COMMANDS]

[2][USAGE]

[3][ARGUMENTS]

[4][OUTPUT]

[5][ENVIRONMENT]

[6][ERROR_HANDLING]

Related Skills

Looking for an alternative to perplexity-tools or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

widget-generator

chat-sdk

zustand

data-fetching