Skip to main content
Glama
enesjakozh
ibrooksSDX

MCP Server for OpenSearch

by ibrooksSDX
OverviewSchemaRelated ServersScoreDiscussions
Python
Hybrid

mcp-server-opensearch：OpenSearch MCP 服务器

铁匠徽章

模型上下文协议 (MCP)是一种开放协议，支持 LLM 应用程序与外部数据源和工具之间的无缝集成。无论您是构建 AI 驱动的 IDE、增强聊天界面，还是创建自定义 AI 工作流，MCP 都提供了一种标准化的方式，将 LLM 与其所需的上下文连接起来。

该存储库是如何为分布式搜索和分析引擎OpenSearch创建 MCP 服务器的示例。

正在建设中

图片1图片2

当前阻止程序 - OpenSearch 的异步客户端未安装

打开搜索异步客户端文档

pip install opensearch-py[async]
zsh: no matches found: opensearch-py[async]

Related MCP server: @git-fabric/aiana

概述

一个基本的模型上下文协议服务器，用于保存和检索开放搜索引擎中的记忆。它充当开放搜索引擎数据库之上的语义记忆层。

成分

工具

  1. search-openSearch

    • 将记忆存储在 OpenSearch 数据库中

    • 输入：

      • query （json）：准备好的json查询消息

    • 返回：确认消息

安装

通过 Smithery 安装

要通过Smithery自动为 Claude Desktop 安装 mcp-server-opensearch：

npx -y @smithery/cli install @ibrooksSDX/mcp-server-opensearch --client claude

使用 uv（推荐）

使用uv时无需特殊安装即可直接运行mcp-server-opensearch 。

uv run mcp-server-opensearch \
  --opensearch-url "http://localhost:9200" \
  --index-name "my_index" \

或者

uv run fastmcp run demo.py:main

测试 - 本地开放搜索客户端

图片4

uv run python src/mcp-server-opensearch/test_opensearch.py

测试 - MCP 服务器连接至 Open Search 客户端

图片1图片2

cd src/mcp-server-opensearch
uv run fastmcp dev demo.py

与 Claude Desktop 一起使用

要将此服务器与 Claude Desktop 应用程序一起使用，请将以下配置添加到claude_desktop_config.json的“mcpServers”部分：

{
  "opensearch": {
    "command": "uvx",
    "args": [
      "mcp-server-opensearch",
      "--opensearch-url",
      "http://localhost:9200",
      "--opensearch-api-key",
      "your_api_key",
      "--index-name",
      "your_index_name"
    ]
  }, "Demo": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "fastmcp",
        "--with",
        "opensearch-py",
        "fastmcp",
        "run",
        "/Users/ibrooks/Documents/GitHub/mcp-server-opensearch/src/mcp-server-opensearch/demo.py"
      ]
    }
}

或者使用 FastMCP UI 将服务器安装到 Claude

uv run fastmcp install demo.py

环境变量

也可以使用环境变量来配置服务器：

  • OPENSEARCH_HOST ：OpenSearch 服务器的 URL，例如http://localhost

  • OPENSEARCH_HOSTPORT ：OpenSearch 服务器主机的端口9200

  • INDEX_NAME ：要使用的索引的名称

This server cannot be installed

A
license - permissive license
Not graded
quality - not tested
D
maintenance

How are these scores calculated?

Maintenance

–Maintainers
–Response time
–Release cycle
–Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • Qdrant MCP Server

    andrewlwn77
    A
    license
    Not graded
    quality
    D
    maintenance
    Provides semantic memory capabilities using Qdrant vector database with configurable embedding providers, allowing storage and retrieval of information using vector similarity.
    2
    Apache 2.0

  • @git-fabric/aiana

    git-fabric
    F
    license
    A
    quality
    Not graded
    maintenance
    A composable semantic memory layer that provides cross-project recall and session context using Qdrant and OpenAI embeddings. It enables users to securely store, search, and manage persistent memories with built-in secret scrubbing for privacy.
    11

View all related MCP servers

Related MCP Connectors

  • goldhold

    Persistent memory for AI agents. Search, store, and recall across sessions.

  • AI Context Flow

    Universal memory for AI agents and tools. Save, organize and search context anywhere.

  • DeepMem

    Mem0-compatible persistent memory for AI agents: write facts once, recall them semantically.

View all MCP Connectors

Appeared in Searches

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ibrooksSDX/mcp-server-opensearch'

If you have feedback or need assistance with the MCP directory API, please join our Discord server