Assistant MCP

一個用於從Pinecone Assistant檢索信息的MCP服務器實現

知識管理與記憶開發者工具 #信息檢索 #Pinecone集成 #MCP服務 .Rust

評分 : 2.5分

下載量 : 28

更新時間 : 2025-04-29

What is Pinecone Assistant MCP Server?

The Pinecone Assistant MCP Server is a bridge service that allows applications to retrieve information from Pinecone Assistant using the standardized Model Context Protocol. It handles authentication and query processing to make assistant data easily accessible.

How to use this service?

You can run the server either through Docker or by building from source. Once running, configure your client application (like Claude Desktop) to connect to this server to access Pinecone Assistant data.

Use Cases

This service is ideal when you need to integrate Pinecone Assistant's capabilities into your existing applications or workflows that support MCP.

Key Features

Pinecone IntegrationSeamlessly connects to Pinecone Assistant to retrieve information

Configurable ResultsSupports retrieving multiple results with adjustable count

MCP Standard ComplianceImplements the Model Context Protocol for standardized access

Pros and Cons

Advantages

Standardized access through MCP protocol

Easy Docker deployment

Flexible configuration options

Limitations

Requires Pinecone API access

Needs Docker or Rust knowledge for source builds

Limited to Pinecone Assistant functionality

Getting Started

Obtain API credentials

Get your Pinecone API key from the Pinecone Console

Build the Docker image

Create the container image using the provided Dockerfile

Run the server

Start the container with your API credentials

Usage Scenarios

Integration with Claude DesktopConfigure Claude Desktop to use this server as an MCP endpoint for Pinecone Assistant access

Testing with InspectorUse the MCP inspector tool to test server functionality

Frequently Asked Questions

Where do I get my Pinecone API key?

Can I run this without Docker?

What is the default Pinecone Assistant host?

Additional Resources

Pinecone Console

Get your API key and manage assistants

Docker Documentation

Learn more about Docker installation and usage

Rust Installation

Install Rust for building from source

🚀 松果助理 MCP 服務器

本項目是一個用於從松果助理檢索信息的 MCP 服務器實現，能夠幫助用戶便捷地從松果助理獲取所需信息，支持可配置數量的多結果檢索。

🚀 快速開始

在使用本服務器前，需要完成一些準備工作，確保系統滿足以下先決條件：

系統上已安裝 Docker
擁有松果 API 密鑰，可在松果控制檯獲取
知曉松果助理 API 主機地址，創建一個 Assistant 後，在 Assistant 詳情頁面可以找到主機地址

✨ 主要特性

從松果助理檢索信息
支持可配置結果數量的多結果檢索

📦 安裝指南

使用 Docker 構建

構建 Docker 鏡像，可使用以下命令：

docker build -t pinecone/assistant-mcp .

使用 Docker 運行

使用你的松果 API 密鑰運行服務器，命令如下：

docker run -i --rm \
  -e PINECONE_API_KEY=<YOUR_PINECONE_API_KEY_HERE> \
  -e PINECONE_ASSISTANT_HOST=<YOUR_PINECONE_ASSISTANT_HOST_HERE> \
  pinecone/assistant-mcp

環境變量

屬性	詳情
`PINECONE_API_KEY`	必需，你的松果 API 密鑰
`PINECONE_ASSISTANT_HOST`	可選，松果助理 API 主機地址（默認值：https://prod-1-data.ke.pinecone.io）
`LOG_LEVEL`	可選，日誌級別（默認值：info）

從源代碼構建

如果你希望不使用 Docker 從源代碼構建，可按以下步驟操作：

確保你已經安裝了 Rust（https://rustup.rs/）
克隆此倉庫
運行 cargo build --release
可執行文件將位於 target/release/assistant-mcp

💻 使用示例

基礎用法

使用 inspector 測試

export PINECONE_API_KEY=<YOUR_PINECONE_API_KEY_HERE>
export PINECONE_ASSISTANT_HOST=<YOUR_PINECONE_ASSISTANT_HOST_HERE>
# 單獨運行 inspector
npx @modelcontextprotocol/inspector cargo run
# 或通過 inspector 使用 Docker 直接運行
npx @modelcontextprotocol/inspector -- docker run -i --rm -e PINECONE_API_KEY -e PINECONE_ASSISTANT_HOST pinecone/assistant-mcp

高級用法

與 Claude Desktop 集成

在你的 claude_desktop_config.json 中添加以下內容：

{
  "mcpServers": {
    "pinecone-assistant": {
      "command": "docker",
      "args": [
        "run", 
        "-i", 
        "--rm", 
        "-e", 
        "PINECONE_API_KEY", 
        "-e", 
        "PINECONE_ASSISTANT_HOST", 
        "pinecone/assistant-mcp"
      ],
      "env": {
        "PINECONE_API_KEY": "<YOUR_PINECONE_API_KEY_HERE>",
        "PINECONE_ASSISTANT_HOST": "<YOUR_PINECONE_ASSISTANT_HOST_HERE>"
      }
    }
  }
}