OpenSearch MCP Server

@loupipalien

Basic information

About OpenSearch MCP Server

OpenSearch MCP Server config

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

{
  "mcpServers": {
    "opensearch-mcp-server": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/loupipalien/opensearch-mcp-server",
        "opensearch-mcp-server"
      ],
      "env": {
        "OPENSEARCH_HOSTS": "your_opensearch_cluster_hosts",
        "OPENSEARCH_USERNAME": "your_opensearch_cluster_username",
        "OPENSEARCH_PASSWORD": "your_opensearch_cluster_password"
      }
    }
  }
}

OpenSearch MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is OpenSearch MCP Server?

An MCP server that lets you interact with an OpenSearch cluster using natural language from any MCP client (Cursor, Cline, etc.). It provides tools for cluster health analysis, document bulk operations, index management, and search.

How to use OpenSearch MCP Server?

Install Python 3.10+ and uv. Add the server configuration to your MCP settings file, setting the environment variables OPENSEARCH_HOSTS, OPENSEARCH_USERNAME, and OPENSEARCH_PASSWORD. Run via remote repo using uvx or from a local repo using uv. For testing, you can start a 2‑node Docker cluster with the provided docker-compose.yml.

Key features of OpenSearch MCP Server?

Get cluster health and statistics
Bulk document operations to indices
Create, delete, and list indices
Retrieve index mappings and info
Search with query DSL
Natural language queries via MCP clients

Use cases of OpenSearch MCP Server?

Monitor cluster health via conversational commands
Bulk index large datasets into OpenSearch
Automate index creation and deletion tasks
Search documents using complex queries
Retrieve index mappings for schema inspection

Frequently asked questions

What are the prerequisites?

Python 3.10 or higher and [uv](https://github.com/astral-sh/uv) must be installed.

How do I configure authentication?

Set the environment variables `OPENSEARCH_USERNAME` and `OPENSEARCH_PASSWORD` in your MCP settings file.

Can I connect to multiple OpenSearch hosts?

Yes. Separate host addresses with commas in the `OPENSEARCH_HOSTS` environment variable.

How can I start a local OpenSearch cluster for testing?

Run `export OPENSEARCH_INITIAL_ADMIN_PASSWORD=your_password` then `docker-compose up -d`. Default credentials: `admin` / `your_opensearch_cluster_password`.

What license does this project use?

Apache v2.0 License.

Comments

More Databases MCP servers

Neon MCP Server

neondatabase

MCP server for interacting with Neon Management API and databases

617

nuzur

nuzur is a model-first database platform for MySQL and PostgreSQL. The MCP server lets any AI assistant or agent (Claude, Cursor, Gemini, or anything else that speaks MCP) design your schema, query your data, generate mi

Schemity

tbson

Local database MCP server: your agent sees a migration's impact before it runs, for PostgreSQL, MySQL, SQL Server and SQLite, with no database credentials.

MCP DB Wizard

srmadscience

Oracle MCP server with no run-sql tool: It generates tools for each of the PL/SQL procedures, tables and approved SQL you choose. The server doesn't expose a SQL prompt, and can't reveal how it's connected to Oracle.

Xata MCP Server

The Xata MCP server lets AI assistants and agents interact with your Xata organizations, projects, and Postgres database branches.