広告掲載
MCP.so
ログイン

Perplexica MCP Server

@thetom42

リポジトリ

基本情報

カテゴリ

その他

ライセンス

MIT license

トランスポート

stdio

作者

thetom42

Perplexica MCP Server について

MCP server for Perplexica

#perplexica#mcp-server#ai-search

Perplexica MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "perplexica": {
      "command": "uvx",
      "args": [
        "perplexica-mcp",
        "stdio"
      ],
      "env": {
        "PERPLEXICA_BACKEND_URL": "http://localhost:3000/api/search"
      }
    }
  }
}

Perplexica MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

What is Perplexica MCP Server?

Perplexica MCP Server is a Model Context Protocol (MCP) server that provides AI-powered web search functionality by connecting MCP clients to the Perplexica search API. It supports stdio, SSE, and Streamable HTTP transports and is built with the FastMCP framework.

How to use Perplexica MCP Server?

Clone the repository, install dependencies with uv sync, and set the PERPLEXICA_BACKEND_URL environment variable to your running Perplexica instance. Run the server using one of three transport modes: uv run src/perplexica_mcp.py stdio, sse, or http. Configuration examples for Claude Desktop, Cursor IDE, and generic MCP clients are provided. Docker deployment is also supported with compose files for HTTP and SSE transports.

Key features of Perplexica MCP Server

  • AI-powered web search with multiple focus modes
  • Supports stdio, SSE, and Streamable HTTP transports
  • Built with FastMCP for robust MCP protocol compliance
  • Single unified server implementation for all transports
  • Docker support with health checks and security best practices

Use cases of Perplexica MCP Server

  • Add AI search to MCP-compatible clients like Claude Desktop or Cursor
  • Provide real-time search results over Server-Sent Events (SSE)
  • Integrate with REST workflows using Streamable HTTP transport
  • Deploy containerized search capabilities alongside Perplexica in Docker networks

よくある質問

1

What transports does Perplexica MCP Server support?

It supports stdio, SSE (Server-Sent Events), and Streamable HTTP transports. Stdio is recommended for most MCP clients; SSE and HTTP are available for web-based or real-time use cases.

2

How do I configure Perplexica MCP Server for my client?

Set the `PERPLEXICA_BACKEND_URL` environment variable to point to your Perplexica instance, then run the server with the appropriate transport command. For Claude Desktop or Cursor, use a stdio configuration with `uv run ... stdio`.

3

Does Perplexica MCP Server require a separate Perplexica instance?

Yes. The server connects to a running Perplexica instance via the `PERPLEXICA_BACKEND_URL`. You must ensure Perplexica is accessible at that URL.

4

How can I run Perplexica MCP Server in Docker?

Docker Compose files are provided for HTTP and SSE transports. Create an external Docker network named `backend`, set environment variables (e.g., `PERPLEXICA_BACKEND_URL`), then run `docker-compose up -d`. Both containers include health checks.

5

How do I test the server?

Run `uv run src/test_transports.py` to verify stdio, SSE, and HTTP transports, including MCP protocol handshake and endpoint accessibility.

コメント

「その他」の他のコンテンツ

P

PickFu MCP

PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct

Blender

ahujasid

Open-source MCP to use Blender with any LLM

23.6K

ICSS

chokcoco

不止于 CSS

20.7K

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K
広告掲載