opensearch-mcp-server-py

What it is and what it does

opensearch-mcp-server-py is a bridge between AI assistants (like Claude) and OpenSearch clusters, implemented as a Model Context Protocol server. It exposes OpenSearch operations—index listing, searching, mapping retrieval, shard inspection, cluster health checks, and more—as tools that LLMs can call during conversations. The server handles authentication (basic auth, IAM roles, header-based, mTLS) and supports dynamic per-call connection parameters, allowing a single agent to work with multiple clusters without reconfiguration.

The package ships with nine core tools enabled by default (search, list indices, get mappings, cluster health, etc.) and ten additional tools available on demand (node info, segment details, query insights, memory management). It supports both traditional stdio transport and streaming protocols (SSE, Streamable HTTP), making it compatible with Claude Desktop, LangChain, and other MCP clients. The agentic memory tools expose OpenSearch's server-side memory API for production pipelines that want centralized memory management.

Use it for:

• Enable Claude or other LLMs to search OpenSearch indices and retrieve results during multi-turn conversations without manual API calls.
• Build agentic systems where AI assistants autonomously query cluster health, shard allocation, and node metrics to diagnose operational issues.
• Integrate OpenSearch into LangChain workflows where agents need structured access to search, mapping, and cluster state APIs.
• Deploy multi-cluster discovery where a single agent dynamically connects to different OpenSearch endpoints based on runtime parameters.
• Centralize memory management in production AI pipelines using OpenSearch's agentic memory API for session and fact extraction.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Provides a Model Context Protocol (MCP) server that enables AI assistants and LLMs to query and manage OpenSearch clusters through a standardized interface supporting both stdio and streaming transports.

Yes, if you are building AI assistants or LLM agents that need to query or manage OpenSearch clusters. The package is actively maintained, has no known vulnerabilities, uses a permissive license, and provides a clean MCP abstraction over OpenSearch APIs. Install friction is low and Python 3.10+ support is current. Not relevant if you do not use OpenSearch or do not need LLM integration.

Install

opensearch-mcp-server-py on PyPI

pip install opensearch-mcp-server-py

uv add opensearch-mcp-server-py

poetry add opensearch-mcp-server-py

Installing opensearch-mcp-server-py

Before you install

Low install friction with a pure-Python wheel distribution. Active maintenance with a recent release (16 days old) and steady repository activity. Requires Python 3.10 or later.

License in practice

Apache-2.0 permissive license allows commercial and private use with minimal restrictions; suitable for most deployment contexts.

Quickstart

pip install opensearch-mcp-server-py

from opensearch_mcp_server_py import OpenSearchMCPServer

server = OpenSearchMCPServer()
server.start()

Requires Python 3.10 or later; an OpenSearch cluster endpoint must be provided either via environment variables or dynamically per tool call.

Verify before relying

• Whether the package includes a CLI entry point or requires programmatic initialization via Python code.
• Whether all 16 runtime dependencies are required for basic operation or if some are optional based on feature selection.
• Performance characteristics and latency overhead when routing queries through the MCP protocol layer.

Package facts

Evidence: opensearch_mcp_server_py-0.11.0-py3-none-any.whl

Tags

More Artificial Intelligence packages

Further reading