MCP-researcher Server
Perplexity MCP サーバー
Perplexityの専用AIモデルを搭載したインテリジェントなリサーチアシスタント。クエリの複雑さを自動検出し、最適な結果を得るために最適なモデルにリクエストをルーティングします。公式サーバーとは異なり、あらゆるタスクに対応する検索機能を備えています。
ツール
クイック ノート: Deep Research ツールは、実装の違いにより、cline などの一部のツールではタイムアウトしますが、cursor などの他のツールではタイムアウトしません。ただし、reason ツールがそれを補います。
1. 検索(Sonar Pro)
簡単なクエリや基本情報の検索に最適なクイック検索。簡潔で直接的な回答が必要な、率直な質問に最適です。
const result = await use_mcp_tool({
server_name: "perplexity",
tool_name: "search",
arguments: {
query: "What is the capital of France?",
force_model: false // Optional: force using this model even if query seems complex
}
});2. Reason(ソナー・リーゾニング・プロ)
詳細な分析を必要とする複雑で多段階のタスクを処理します。説明、比較、問題解決に最適です。
const result = await use_mcp_tool({
server_name: "perplexity",
tool_name: "reason",
arguments: {
query: "Compare and contrast REST and GraphQL APIs, explaining their pros and cons",
force_model: false // Optional: force using this model even if query seems simple
}
});3. ディープリサーチ(ソナーディープリサーチ)
包括的な調査を実施し、詳細なレポートを作成します。複雑なトピックの詳細な分析に最適です。
const result = await use_mcp_tool({
server_name: "perplexity",
tool_name: "deep_research",
arguments: {
query: "The impact of quantum computing on cryptography",
focus_areas: [
"Post-quantum cryptographic algorithms",
"Timeline for quantum threats",
"Practical mitigation strategies"
],
force_model: false // Optional: force using this model even if query seems simple
}
});Related MCP server: github-manager MCP Server
インテリジェントなモデル選択
サーバーはクエリの複雑さを自動的に分析し、リクエストを最も適切なモデルにルーティングします。
シンプルなクエリ→ Sonar Pro
基本情報の検索
率直な質問
簡単な事実
複雑なクエリ→ Sonar Reasoning Pro
どのように/なぜの質問
比較
ステップバイステップの説明
問題解決タスク
リサーチクエリ→ Sonar Deep Research
詳細な分析
包括的な研究
詳細な調査
多面的なトピック
任意のツールの引数でforce_model: trueを使用して自動選択をオーバーライドできます。
設定
前提条件
Node.js ( nodejs.orgから)
Perplexity API キー ( perplexity.ai/settings/apiから)
リポジトリをどこかにクローンする
MCP設定を構成する
MCP 設定ファイルに追加します (場所はプラットフォームによって異なります)。
{
"mcpServers": {
"perplexity": {
"command": "node",
"args": ["/path/to/perplexity-server/build/index.js"],
"env": {
"PERPLEXITY_API_KEY": "YOUR_API_KEY_HERE"
},
"disabled": false,
"autoApprove": []
}
}
}または、NPX を使用すると、ローカルにインストールする必要がなくなります (macOS に推奨)。
{
"mcpServers": {
"perplexity": {
"command": "npx",
"args": [
"-y",
"perplexity-mcp"
],
"env": {
"PERPLEXITY_API_KEY": "your_api_key"
}
}
}
}Available Tools
3 toolsdeep_researchB
Conducts in-depth analysis and generates detailed reports using Perplexity's Sonar Deep Research model. Best for comprehensive research topics.
Inputs: query (required), focus_areas, force_model.
reasonA
Handles complex, multi-step tasks using Perplexity's Sonar Reasoning Pro model. Best for explanations, comparisons, and problem-solving.
Inputs: query (required), force_model.
searchA
Quick search for simple queries using Perplexity's Sonar Pro model. Best for straightforward questions and basic information lookup.
Inputs: query (required), force_model.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: deep_research for comprehensive analysis, reason for multi-step reasoning tasks, and search for basic queries. The descriptions explicitly differentiate their use cases, eliminating any ambiguity or overlap in functionality.
All tool names follow a consistent snake_case pattern with clear, descriptive verbs (deep_research, reason, search). There are no deviations in naming style, making the set predictable and easy to understand.
With only 3 tools, the set feels thin for a research server, potentially limiting coverage of common research workflows like summarization, citation management, or data extraction. However, the tools are well-scoped to core research tasks, avoiding bloat.
The tools cover basic research functions (deep analysis, reasoning, quick search), but there are notable gaps such as no tools for summarizing, filtering results, or handling citations. This may cause agents to work around missing operations in complex research scenarios.
Maintenance
Related MCP Connectors
Google Keep-style notes app with an MCP server for AI agents to read/write notes.
Markdown-based note-taking with a hosted MCP server. Your notes serve you and your AI.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
An MCP server that used to create notes
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceThis TypeScript-based MCP server enables users to manage and summarize text notes, providing tools for note creation and summarization prompts.3,487 npm10MIT
- AlicenseNot gradedqualityNot gradedmaintenanceThis TypeScript-based MCP server enables users to manage a simple notes system with capabilities to create and summarize notes through structured prompts and resources.1 npm-
- AlicenseNot gradedqualityDmaintenanceThis TypeScript-based server implements a simple notes system, allowing users to create and manage text notes and generate summaries, showcasing core MCP concepts.60 npm16Apache 2.0
- AlicenseNot gradedqualityDmaintenanceThis TypeScript-based MCP server allows users to manage a simple notes system through creating and summarizing text notes using Model Context Protocol (MCP).2,105 npm8MIT