mcp-server-opensearch: An OpenSearch MCP Server

@MCP-Mirror

Repository

Basic information

About mcp-server-opensearch: An OpenSearch MCP Server

Mirror of

#mcp-server #opensearch #model-context-protocol

mcp-server-opensearch: An OpenSearch MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "ibrooksSDX_mcp-server-opensearch": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli",
        "install",
        "@ibrooksSDX/mcp-server-opensearch",
        "--client",
        "claude"
      ]
    }
  }
}

mcp-server-opensearch: An OpenSearch MCP Server tools

`query` (json): prepared json query message

Confirmation message

Overview

What is mcp-server-opensearch?

mcp-server-opensearch is a basic Model Context Protocol (MCP) server that acts as a semantic memory layer on top of the OpenSearch distributed search and analytics engine. It is designed for developers who need to integrate LLM applications with OpenSearch for storing and retrieving memories.

How to use mcp-server-opensearch?

Install automatically via Smithery (npx -y @smithery/cli install @ibrooksSDX/mcp-server-opensearch --client claude) or run directly with uv run mcp-server-opensearch --opensearch-url "http://localhost:9200" --index-name "my_index". Configuration can also be done via environment variables (OPENSEARCH_HOST, OPENSEARCH_HOSTPORT, INDEX_NAME). For local development, use fastmcp dev demo.py. Use with Claude Desktop by adding a configuration entry to claude_desktop_config.json.

Key features of mcp-server-opensearch

Semantic memory layer on OpenSearch
Single tool: search-openSearch
Supports query via JSON input
Configurable via CLI flags or environment variables
Integrates with Claude Desktop via MCP
Installation via Smithery or uv

Use cases of mcp-server-opensearch

Storing and retrieving LLM conversation memories in OpenSearch
Providing persistent context for AI assistants
Building a memory layer for custom AI workflows
Adding searchable memory to MCP‑compatible chat interfaces

Frequently asked questions

What is the Model Context Protocol?

MCP is an open protocol that enables seamless integration between LLM applications and external data sources and tools, providing a standardized way to connect LLMs with the context they need.

What dependencies are required?

The server uses `opensearch-py` with async support, but installation currently has a blocker: `pip install opensearch-py[async]` fails due to shell expansion. The recommended runtime is `uv`.

How do I configure the server?

You can pass `--opensearch-url`, `--opensearch-api-key`, and `--index-name` as command‑line arguments, or set the environment variables `OPENSEARCH_HOST`, `OPENSEARCH_HOSTPORT`, and `INDEX_NAME`.

What is the current development status?

The project is under construction; the async client for OpenSearch is not yet installing correctly, and work is ongoing to resolve that blocker.

How do I test the server?

Run the local OpenSearch client test with `uv run python src/mcp-server-opensearch/test_opensearch.py`, then test the MCP server connection with `cd src/mcp-server-opensearch && uv run fastmcp dev demo.py`.