Skip to main content
Glama
enesjakozh
letsbuildagent

Perplexity Tool for Claude Desktop

by letsbuildagent
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Claudeデスクトップ用のPerplexityツール

Perplexity AI の API を Claude Desktop と統合するカスタム MCP ツール。これにより、Claude は Web ベースの調査を実行し、引用付きの回答を提供できるようになります。

前提条件のインストール

  1. Git をインストールします。

    • Macの場合:

      • まずターミナルにこれを貼り付けてHomebrewをインストールします: GXP1

      • 次にGitをインストールします: GXP2

    • Windowsの場合:

      • git-scm.comからGitをダウンロードする

      • インストーラーを実行する

  2. Node.js をインストールします。

    • Macの場合:

      brew install node

    • Windowsの場合:

      • nodejs.orgからダウンロード

      • インストーラーを実行する

  3. 次のコマンドを実行してインストールを確認します。

git --version
node --version

Related MCP server: Perplexity MCP Server

ツールのインストール

  1. リポジトリをクローンする

git clone https://github.com/letsbuildagent/perplexity-tool
cd perplexity-tool

  1. 依存関係をインストールする

npm install

  1. APIキーを設定する

次の 2 つのオプションがあります。

オプション 1 (クイックセットアップ):

  • server.jsを開く

  • 次の行を見つけます:

const PERPLEXITY_API_KEY = "YOUR-API-KEY-HERE";

  • Perplexity APIキーに置き換えてください

オプション 2 (ベストプラクティス):

  • .env ファイルを作成します。

    # On Mac/Linux:
touch .env
open .env

# On Windows:
notepad .env

    または、テキストエディタで.envという名前の新しいファイルを作成するだけです。

  • API キーを .env ファイルに追加します。

    PERPLEXITY_API_KEY=your-api-key-here

  • dotenvをインストールします。

    npm install dotenv

  • server.js を更新します。

    import 'dotenv/config'
const PERPLEXITY_API_KEY = process.env.PERPLEXITY_API_KEY;

  1. Claudeデスクトップの設定

  • ~/Library/Application Support/Claude/claude_desktop_config.jsonを開きます。

  • 次の構成を追加します。

{
  "mcpServers": {
    "perplexity-tool": {
      "command": "node",
      "args": [
        "/full/path/to/perplexity-tool/server.js"
      ]
    }
  }
}

/full/path/toリポジトリのクローンを作成した実際のパスに置き換えます。

  1. Claudeデスクトップを再起動します

使用法

インストールが完了すると、次のようなコマンドを使用して Claude 経由でツールを使用できるようになります。

  • 「AIの最新動向についてPerplexityに聞いてみよう」

  • 「Perplexity を使って量子コンピューティングの歴史を研究する」

  • 「気候変動に関する情報をPerplexityで検索し、過去1か月に焦点を当てる」

詳細オプション

追加のパラメータを指定できます:

  • temperature : 応答のランダム性を制御します（0-2）

  • max_tokens : レスポンスの長さを制限する

  • search_domain_filter : 検索を特定のドメインに制限します

  • search_recency_filter : 期間（日/週/月/年）でフィルタリングします

トラブルシューティング

  1. Gitが見つかりません:

    • Gitが正しくインストールされていることを確認してください

    • 端末を再起動してみてください

    • Macでは、HomebrewがPATHに入っていることを確認してください。

  2. Node.js エラー:

    • node --versionで Node.js のインストールを確認する

    • Node.jsを再インストールしてみてください

  3. API キーの問題:

    • APIキーを正しくコピーしたことを確認してください

    • .envファイルに余分なスペースがないことを確認してください

    • オプション2を使用する場合は、dotenvがインストールされていることを確認してください。

  4. Claude にツールが表示されない:

    • claude_desktop_config.json のパスを確認してください

    • パスがserver.jsファイルを指していることを確認してください

    • Claudeデスクトップを再起動します

    • コンソールにエラーメッセージがないか確認してください

ライセンス

マサチューセッツ工科大学

セキュリティに関する注意事項

コードを共有したり公開したりする予定がある場合:

  • APIキーをGitにコミットしないでください

  • .env メソッドを使用する (オプション 2)

  • .gitignore ファイルに .env を追加します

Available Tools

1 tool
ask_perplexityC

Ask a question to Perplexity AI

ParametersJSON Schema
NameRequiredDescriptionDefault
questionYesThe question to ask
temperatureNoResponse randomness (0-2)
max_tokensNoMaximum tokens in response
search_domain_filterNoLimit search to specific domains
search_recency_filterNoFilter results by recencymonth

TDQS

C2.7/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool 'Ask a question to Perplexity AI,' which implies it's a query tool, but doesn't describe what happens—e.g., whether it performs web searches, generates responses, has rate limits, or requires authentication. This is a significant gap for a tool with multiple parameters and no output schema.

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 description is a single, clear sentence with no wasted words. It's front-loaded and efficiently conveys the core action, making it easy to scan and understand quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (5 parameters, no annotations, no output schema), the description is incomplete. It doesn't explain what the tool returns, how it behaves (e.g., search-based vs. generative), or any constraints. The agent must rely heavily on the schema and tool name, which is insufficient for effective use.

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?

The input schema has 100% description coverage, so parameters like 'question,' 'temperature,' and 'search_recency_filter' are well-documented in the schema. The description adds no additional meaning beyond the schema, such as explaining how parameters interact or typical use cases. This meets the baseline of 3 since the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Ask a question to Perplexity AI' clearly states the action (ask) and target (Perplexity AI), which is adequate. However, it's somewhat vague about what Perplexity AI is or does—it doesn't specify if this is for general queries, research, or something else. With no sibling tools, differentiation isn't needed, but the purpose could be more specific.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool—it doesn't mention use cases, prerequisites, or alternatives. With no sibling tools, there's no need to differentiate, but it lacks any context for appropriate usage, leaving the agent to infer based on the tool name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev1.0.0
    • Addedask_perplexity
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

C2.9/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'ask_perplexity' has a clearly distinct purpose that cannot be confused with any other tool in this server.

Naming Consistency5/5

The single tool name follows a clear verb_noun pattern ('ask_perplexity'), and with only one tool, there is perfect consistency. No other naming conventions exist to create inconsistency.

Tool Count2/5

A single tool is generally too few for most server purposes, as it provides minimal functionality and limits agent capabilities. For a Perplexity AI integration, one tool might suffice for basic queries, but it feels thin and lacks operations like follow-up questions or context management.

Completeness2/5

The tool surface is severely incomplete for interacting with Perplexity AI. While 'ask_perplexity' covers basic queries, there are significant gaps such as no support for conversation history, context setting, or handling different query types, which will likely cause agent failures in complex tasks.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

  • pixserpA
    com.pixserp

    Live AI-native web search with citations. One tool for every MCP client. Flat per-request pricing.

    SearchBrowser Automation
    12
  • ScrapeNestOAuth
    dev.scrapenest

    Web search, scraping, RAG answers with citations, and translation as MCP tools.

    Web ScrapingRAG SystemsSearch
    2
  • Manifold MCPA
    com.manifoldmcp

    An MCP for marketers that gives agents tools for SEO, AEO, socials and ads data. Generous free tier; works in Claude, ChatGPT, Cursor and other MCP clients.

    MarketingSearchSocial Media
    811
  • AIsa Web Search & ResearchAOAuth
    one.aisa

    Your agent needs the open web — searched by more than one engine, and read as clean markdown rather than raw HTML. **What you can ask for** • "Search this question with two providers and tell me where they disagree." • "Scrape these 40 URLs into markdown, in one batch." • "Crawl this documentation site and give me every page." • "Do deep research on this topic and cite the sources." • "Find the academic papers behind this claim." **How to use it** Point any MCP client at https://mcp.aisa.one/search/mcp and sign in with OAuth — there is no key to create or paste. 30 tools across several independent providers: Tavily and Exa search, answers, contents and agent runs; Firecrawl scrape, batch scrape, crawl, map and search; Perplexity Sonar, Sonar Pro, reasoning and deep research; Oxylabs AI search and LLM jobs; OpenAI and Anthropic web search; and scholarly search. **Why this rather than the source** Several independent indexes behind one account, because one engine's blind spot is not visible from inside it. **It is also a door to the rest** The same login reaches 26 sources and 580+ operations. Find the page here, then ask the same agent who links to it or how much traffic it gets — without adding a second server. **What it costs** Finding and inspecting an operation is free. Running one is billed per call at API prices, with no seat and no monthly minimum, and every call takes max_price_usd so an agent cannot overspend by accident. **Where else it reaches** https://mcp.aisa.one/seo-serp/mcp for the Google results page itself, https://mcp.aisa.one/seo-serp-other-engines/mcp for Bing, Baidu and Naver.

    Browser AutomationSearchWeb Scraping
    351

Related MCP Servers

  • Perplexity MCP Server

    RossH121
    A
    license
    A
    quality
    D
    maintenance
    An MCP server that enables Claude to perform web searches using Perplexity's API with intelligent model selection based on query intent and support for domain and recency filtering.
    6
    4
    MIT

  • Perplexity MCP Server

    Rohit-Seelam
    F
    license
    A
    quality
    D
    maintenance
    Integrates Perplexity AI's search-enhanced language models with Claude Desktop, providing three tools with different complexity levels for quick fact-checking, technical analysis, and deep research.
    3
    2
    -

Appeared in Searches