What is Mcp Server Opensearch

mcp-server-opensearch is an implementation of the Model Context Protocol (MCP) designed to facilitate seamless integration between Large Language Model (LLM) applications and external data sources using OpenSearch, a distributed search and analytics engine.

Use cases

Use cases include enhancing AI-powered IDEs, improving chatbots with contextual memory, and creating custom AI workflows that require efficient data retrieval and management.

How to use

To use mcp-server-opensearch, you can install it via Smithery or run it directly using uv. Configuration involves specifying the OpenSearch URL and index name, and it can be integrated with applications like Claude Desktop by modifying the configuration file.

Key features

Key features include the ability to store and retrieve memories in the OpenSearch engine, acting as a semantic memory layer, and providing a standardized way to connect LLMs with necessary context.

Where to use

mcp-server-opensearch is suitable for various fields including AI development, chat interfaces, and custom AI workflows where integration with external data sources is required.

mcp-server-opensearch: An OpenSearch MCP Server

The Model Context Protocol (MCP) is an open protocol that enables seamless integration between LLM applications and external data sources and tools. Whether you’re building an AI-powered IDE, enhancing a chat interface, or creating custom AI workflows, MCP provides a standardized way to connect LLMs with the context they need.

This repository is an example of how to create a MCP server for OpenSearch, a distributed search and analytics engine.

Under Contruction

Current Blocker - Async Client from OpenSearch isn’t installing

Open Search Async Client Docs

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

Overview

A basic Model Context Protocol server for keeping and retrieving memories in the OpenSearch engine.
It acts as a semantic memory layer on top of the OpenSearch database.

Components

Tools

1. search-openSearch
   • Store a memory in the OpenSearch database
   • Input:
     • query (json): prepared json query message
   • Returns: Confirmation message

Installation

Installing via Smithery

To install mcp-server-opensearch for Claude Desktop automatically via Smithery:

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

Using uv (recommended)

When using uv no specific installation is needed to directly run mcp-server-opensearch.

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

or

uv run fastmcp run demo.py:main

Testing - Local Open Search Client

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

Testing - MCP Server Connection to Open Search Client

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

Usage with Claude Desktop

To use this server with the Claude Desktop app, add the following configuration to the “mcpServers” section of your claude_desktop_config.json:

{
  "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"
    ]
  }
}

Or use the FastMCP UI to install the server to Claude

uv run fastmcp install demo.py

Environment Variables

The configuration of the server can be also done using environment variables:

• OPENSEARCH_HOST: URL of the OpenSearch server, e.g. http://localhost
• OPENSEARCH_HOSTPORT: Port of the host of the OpenSearch server 9200
• INDEX_NAME: Name of the index to use