MCP.so
ログイン

OpenSearch MCP Server

@seohyunjun

OpenSearch MCP Server について

OpenSearch MCP Server: Open-source search cluster management component

基本情報

カテゴリ

データベース

ライセンス

Apache-2.0

ランタイム

python

トランスポート

stdio

公開者

seohyunjun

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": {
    "opensearch": {
      "command": "uv",
      "args": [
        "--directory",
        "path/to/src/opensearch_mcp_server",
        "run",
        "opensearch-mcp-server"
      ],
      "env": {
        "OPENSEARCH_HOST": "https://localhost:9200",
        "OPENSEARCH_USERNAME": "opensearch",
        "OPENSEARCH_PASSWORD": "test123",
        "DASHBOARDS_HOST": "https://localhost:5601"
      }
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is OpenSearch MCP Server?

OpenSearch MCP Server is a Model Context Protocol (MCP) server implementation that provides OpenSearch interaction, enabling searching documents, analyzing indices, and managing a cluster through a set of tools. It is a fork of the Elasticsearch MCP Server converted to work with OpenSearch.

How to use OpenSearch MCP Server?

Clone the repository, then configure Claude Desktop’s config file (claude_desktop_config.json) with the uv command pointing to the local source directory. Set environment variables OPENSEARCH_HOST, OPENSEARCH_USERNAME, OPENSEARCH_PASSWORD, and DASHBOARDS_HOST. Restart Claude Desktop to load the server.

Key features of OpenSearch MCP Server

  • List all indices in the OpenSearch cluster.
  • Retrieve mapping configuration for a specific index.
  • Get settings configuration for a specific index.
  • Search documents using OpenSearch Query DSL.
  • Get health status of the cluster.
  • Get statistical information about the cluster.

Use cases of OpenSearch MCP Server

  • Query documents in an OpenSearch index via natural language.
  • Monitor cluster health and statistics through an AI assistant.
  • Explore index mappings and settings without the Dev Tools console.
  • Automate index management tasks using conversational commands.

FAQ from OpenSearch MCP Server

How does OpenSearch MCP Server authenticate to the OpenSearch cluster?

Authentication is handled via environment variables OPENSEARCH_USERNAME and OPENSEARCH_PASSWORD. The server uses these credentials to connect to the host specified in OPENSEARCH_HOST.

What are the runtime dependencies?

The server requires uv (Python package manager) and the source code cloned from the repository. No additional system-wide installations are described beyond a Python environment.

Can I run the server without a local Docker cluster?

The README shows starting an OpenSearch cluster with Docker Compose, but the server itself only requires a reachable OpenSearch host. You can point it at any existing cluster by configuring the environment variables.

Does the server support OpenSearch Dashboards?

Yes, it includes a DASHBOARDS_HOST environment variable to connect to Dashboards (Kibana equivalent) for UI access.

What transport and security options are available?

The server uses MCP (stdio-based) transport. Security is provided by the username/password authentication sent over HTTPS (the example uses https://localhost:9200).

コメント

「データベース」の他のコンテンツ