MCP Cosmosdb Sql

@hendrickcastro

リポジトリ

基本情報

カテゴリ

データベース

トランスポート

stdio

作者

hendrickcastro

投稿者

H. C.

MCP Cosmosdb Sql について

A comprehensive **Model Context Protocol (MCP)** server for **Azure CosmosDB** database operations. This server provides 8 powerful tools for document database analysis, container discovery, and data querying through the MCP protocol.

MCP Cosmosdb Sql 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": {
    "mcp-cosmosdb": {
      "command": "npx",
      "args": [
        "-y",
        "hendrickcastro/MCPCosmosDB"
      ],
      "env": {
        "OCONNSTRING": "AccountEndpoint=https://your-cosmos-account.documents.azure.com:443/;AccountKey=your-account-key-here;",
        "COSMOS_DATABASE_ID": "your-database-name"
      }
    }
  }
}

MCP Cosmosdb Sql 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 Mcp Cosmosdb Sql?

Mcp Cosmosdb Sql is a comprehensive Model Context Protocol (MCP) server for Azure CosmosDB database operations. It provides eight tools for document database analysis, container discovery, and data querying through the MCP protocol, targeting developers using MCP-compatible clients like Claude Desktop or Cursor IDE.

How to use Mcp Cosmosdb Sql?

Install and configure by adding the server to your MCP client’s JSON configuration (e.g., claude_desktop_config.json) with the command npx -y hendrickcastro/MCPCosmosDB and environment variables OCONNSTRING and COSMOS_DATABASE_ID. Alternatively, clone the repository, run npm install && npm run build, and point the client to dist/server.js. Invoke any of the eight tools via the client’s MCP interface.

Key features of Mcp Cosmosdb Sql

List all databases in the CosmosDB account
List and get detailed information about containers
Execute SQL queries against containers with parameters
Retrieve documents with optional filters and partition key targeting
Retrieve a specific document by ID and partition key
Analyze document schema structure in containers
Performance metrics with query request charges
Automatic connection pooling and retry logic

Use cases of Mcp Cosmosdb Sql

Container analysis: list containers, view index policies, and get statistics
Querying data: run parameterized SQL queries and retrieve filtered documents
Document operations: fetch specific documents by ID and partition key
Schema analysis: understand data patterns and document structures in a container

よくある質問

How do I connect to Azure CosmosDB?

Set the `OCONNSTRING` environment variable to your CosmosDB connection string (including AccountEndpoint and AccountKey) and set `COSMOS_DATABASE_ID` to your database name.

What tools are available?

Eight tools: `mcp_list_databases`, `mcp_list_containers`, `mcp_container_info`, `mcp_container_stats`, `mcp_execute_query`, `mcp_get_documents`, `mcp_get_document_by_id`, and `mcp_analyze_schema`.

What should I do if I get a “Cross partition query required” error?

Set `enable_cross_partition: true` in your query parameters, or increase the `COSMOS_ENABLE_CROSS_PARTITION_QUERY` environment variable.

Can I use the CosmosDB Emulator for local development?

Yes. Use the default emulator connection string (`AccountEndpoint=https://localhost:8081/;AccountKey=C2y6yDjf5/…`) and ensure the emulator is running on port 8081.

How do I configure retry behavior?

Set optional environment variables: `COSMOS_MAX_RETRY_ATTEMPTS` (default 9) and `COSMOS_MAX_RETRY_WAIT_TIME` in milliseconds (default 30000).

「データベース」の他のコンテンツ

Elasticsearch MCP Server

elastic

685

golfdata.online - Verified Golf Clubs

golfdata.online

Verified golf club data for AI agents: holes, par, address, phone, booking links, facilities, visitor rules and green fees for golf clubs in Spain (Canary Islands and mainland), expanding across Europe. Every fact comes

Expired Domains MCP | Karma.Domains

karma-domains

Connect Karma.Domains to ChatGPT, Claude, Cursor, VS Code, or another MCP client — and find a domain in plain language. The same auctions, expired, backorder, and buy-now data you use in the app, plus saved filters, note