Skip to main content
Glama
Elasticsearch/OpenSearch MCP Server

Elasticsearch/OpenSearch MCP Server

by Rbedoyag

Elasticsearch/OpenSearch MCP Server

Overview

A Model Context Protocol (MCP) server implementation that provides Elasticsearch and OpenSearch interaction. This server enables searching documents, analyzing indices, and managing cluster through a set of tools.

Related MCP server: Elasticsearch MCP Server

Features

General Operations

  • general_api_request: Perform a general HTTP API request. Use this tool for any Elasticsearch/OpenSearch API that does not have a dedicated tool.

Index Operations

  • list_indices: List all indices.

  • get_index: Returns information (mappings, settings, aliases) about one or more indices.

  • create_index: Create a new index.

  • delete_index: Delete an index.

Document Operations

  • search_documents: Search for documents.

  • index_document: Creates or updates a document in the index.

  • get_document: Get a document by ID.

  • delete_document: Delete a document by ID.

  • delete_by_query: Deletes documents matching the provided query.

Cluster Operations

  • get_cluster_health: Returns basic information about the health of the cluster.

  • get_cluster_stats: Returns high-level overview of cluster statistics.

Alias Operations

  • list_aliases: List all aliases.

  • get_alias: Get alias information for a specific index.

  • put_alias: Create or update an alias for a specific index.

  • delete_alias: Delete an alias for a specific index.

Configure Environment Variables

Copy the .env.example file to .env and update the values accordingly.

Start Elasticsearch/OpenSearch Cluster

Start the Elasticsearch/OpenSearch cluster using Docker Compose:

# For Elasticsearch
docker-compose -f docker-compose-elasticsearch.yml up -d

# For OpenSearch
docker-compose -f docker-compose-opensearch.yml up -d

The default Elasticsearch username is elastic and password is test123. The default OpenSearch username is admin and password is admin.

You can access Kibana/OpenSearch Dashboards from http://localhost:5601.

Stdio

Option 1: Using uvx

Using uvx will automatically install the package from PyPI, no need to clone the repository locally. Add the following configuration to 's config file claude_desktop_config.json.

// For Elasticsearch
{
  "mcpServers": {
    "elasticsearch-mcp-server": {
      "command": "uvx",
      "args": [
        "elasticsearch-mcp-server"
      ],
      "env": {
        "ELASTICSEARCH_HOSTS": "https://localhost:9200",
        "ELASTICSEARCH_USERNAME": "elastic",
        "ELASTICSEARCH_PASSWORD": "test123"
      }
    }
  }
}

// For OpenSearch
{
  "mcpServers": {
    "opensearch-mcp-server": {
      "command": "uvx",
      "args": [
        "opensearch-mcp-server"
      ],
      "env": {
        "OPENSEARCH_HOSTS": "https://localhost:9200",
        "OPENSEARCH_USERNAME": "admin",
        "OPENSEARCH_PASSWORD": "admin"
      }
    }
  }
}

Option 2: Using uv with local development

Using uv requires cloning the repository locally and specifying the path to the source code. Add the following configuration to Claude Desktop's config file claude_desktop_config.json.

// For Elasticsearch
{
  "mcpServers": {
    "elasticsearch-mcp-server": {
      "command": "uv",
      "args": [
        "--directory",
        "path\\to_folder_proyect\\elasticsearch_mcp_server",
        "run",
        "elasticsearch-mcp-server"
      ],
      "env": {
        "ELASTICSEARCH_HOSTS": "https://localhost:9200",
        "ELASTICSEARCH_USERNAME": "elastic",
        "ELASTICSEARCH_PASSWORD": "test123"
      }
    }
  }
}

// For OpenSearch
{
  "mcpServers": {
    "opensearch-mcp-server": {
      "command": "uv",
      "args": [
        "--directory",
        "path\\to_folder_proyect\\elasticsearch-mcp-server",
        "run",
        "opensearch-mcp-server"
      ],
      "env": {
        "OPENSEARCH_HOSTS": "https://localhost:9200",
        "OPENSEARCH_USERNAME": "admin",
        "OPENSEARCH_PASSWORD": "admin",
        "OPENSEARCH_VERIFY_CERTS": "false"
      }
    }
  }
}

SSE

Option 1: Using uvx

# export environment variables
export ELASTICSEARCH_HOSTS="https://localhost:9200"
export ELASTICSEARCH_USERNAME="elastic"
export ELASTICSEARCH_PASSWORD="test123"

# By default, the SSE MCP server will serve on http://127.0.0.1:8000/sse
uvx elasticsearch-mcp-server --transport sse

# The host, port, and path can be specified using the --host, --port, and --path options
uvx elasticsearch-mcp-server --transport sse --host 0.0.0.0 --port 8000 --path /sse

Option 2: Using uv


py -m pip install u #LOCAL MACHINE
pip install uv     #VIRTUAL ENV

# By default, the SSE MCP server will serve on http://127.0.0.1:8000/sse
uv run src/server.py elasticsearch-mcp-server --transport sse
uv run src/server.py opensearch-mcp-server --transport sse

# The host, port, and path can be specified using the --host, --port, and --path options
uv run src/server.py elasticsearch-mcp-server --transport sse --host 0.0.0.0 --port 8000 --path /sse
uv run src/server.py opensearch-mcp-server --transport sse --host 0.0.0.0 --port 8000 --path /sse
opensearch-mcp-server

Streamable HTTP

Option 1: Using uvx

# export environment variables
export ELASTICSEARCH_HOSTS="https://localhost:9200"
export ELASTICSEARCH_USERNAME="elastic"
export ELASTICSEARCH_PASSWORD="test123"

# By default, the Streamable HTTP MCP server will serve on http://127.0.0.1:8000/mcp
uvx elasticsearch-mcp-server --transport streamable-http

# The host, port, and path can be specified using the --host, --port, and --path options
uvx elasticsearch-mcp-server --transport streamable-http --host 0.0.0.0 --port 8000 --path /mcp

Option 2: Using uv


py -m pip install u #LOCAL MACHINE
pip install uv     #VIRTUAL ENV
# By default, the Streamable HTTP MCP server will serve on http://127.0.0.1:8000/mcp
uv run src/server.py elasticsearch-mcp-server --transport streamable-http

# The host, port, and path can be specified using the --host, --port, and --path options
uv run src/server.py elasticsearch-mcp-server --transport streamable-http --host 0.0.0.0 --port 8000 --path /mcp
uv run src/server.py opensearch-mcp-server --transport streamable-http --host 0.0.0.0 --port 8000 --path /mcp

License

This project is licensed under the Apache License Version 2.0 - see the LICENSE file for details.

Available Tools

16 tools
create_indexC
        Create a new index.
        
        Args:
            index: Name of the index
            body: Optional index configuration including mappings and settings
        

Inputs: index (required), body.

delete_aliasC
        Delete an alias for a specific index.

        Args:
            index: Name of the index
            name: Name of the alias
        

Inputs: index (required), name (required).

delete_by_queryC
        Deletes documents matching the provided query.
        
        Args:
            index: Name of the index
            body: Query to match documents for deletion
        

Inputs: index (required), body (required).

delete_documentC
        Delete a document by ID.
        
        Args:
            index: Name of the index
            id: Document ID
        

Inputs: index (required), id (required).

delete_indexC
        Delete an index.
        
        Args:
            index: Name of the index
        

Inputs: index (required).

general_api_requestB

Perform a general HTTP API request. Use this tool for any Elasticsearch/OpenSearch API that does not have a dedicated tool.

        Args:
            method: HTTP method (GET, POST, PUT, DELETE, etc.)
            path: API endpoint path
            params: Query parameters
            body: Request body
        

Inputs: method (required), path (required), params, body.

get_aliasC
        Get alias information for a specific index.

        Args:
            index: Name of the index
        

Inputs: index (required).

get_cluster_healthB

Returns basic information about the health of the cluster.

Inputs: no named parameters.

get_cluster_statsB

Returns high-level overview of cluster statistics.

Inputs: no named parameters.

get_documentC
        Get a document by ID.
        
        Args:
            index: Name of the index
            id: Document ID
        

Inputs: index (required), id (required).

get_indexC
        Returns information (mappings, settings, aliases) about one or more indices.
        
        Args:
            index: Name of the index
        

Inputs: index (required).

index_documentC
        Creates or updates a document in the index.
        
        Args:
            index: Name of the index
            document: Document data
            id: Optional document ID
        

Inputs: index (required), document (required), id.

list_aliasesB

List all aliases.

Inputs: no named parameters.

list_indicesB

List all indices.

Inputs: no named parameters.

put_aliasC
        Create or update an alias for a specific index.

        Args:
            index: Name of the index
            name: Name of the alias
            body: Alias configuration
        

Inputs: index (required), name (required), body (required).

search_documentsD
        Search for documents.
        
        Args:
            index: Name of the index
            body: Search query
        

Inputs: index (required), body (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.3/5.0

    Scored across 16 tools

    Disambiguation5/5

    Every tool has a clearly distinct purpose targeting specific resources and actions in Elasticsearch/OpenSearch. The tools cover index management, document operations, alias handling, cluster monitoring, and search with no overlapping functionality. Even the general_api_request tool is clearly distinguished as a fallback for unsupported APIs.

    Naming Consistency5/5

    The tools follow a highly consistent verb_noun naming pattern throughout (e.g., create_index, delete_document, get_cluster_health, search_documents). All tools use snake_case with clear action verbs followed by resource nouns, making the API surface predictable and readable.

    Tool Count5/5

    With 16 tools, this server is well-scoped for the Elasticsearch/OpenSearch domain. It provides comprehensive coverage of core operations without being overwhelming. Each tool serves a specific, necessary function in the database management workflow, and the count aligns well with the complexity of the domain.

    Completeness4/5

    The toolset provides excellent coverage of core Elasticsearch/OpenSearch operations including CRUD for indices and documents, alias management, cluster monitoring, and search. The general_api_request tool elegantly handles edge cases. Minor gaps might include bulk operations or specific monitoring endpoints, but agents can work around these using the general tool.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      MCP server for OpenSearch that enables AI assistants to interact with OpenSearch clusters through a standardized interface for search, index management, and cluster operations.
      9
      40,158 PyPI
      158
      Apache 2.0
    • A
      license
      Not graded
      quality
      D
      maintenance
      MCP server that provides tools and resources to interact with Elasticsearch clusters, including listing indices, searching, and retrieving mappings.
      3
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that enables AI assistants to directly interact with Elasticsearch for searching, aggregating, and retrieving documents from indices, supporting full-text search, semantic search, and various query modes.
      29 npm
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Read-only MCP server for exploring and searching OpenSearch clusters, enabling log analysis, index exploration, and query execution.
      8
      MIT