MCP Catalogs
Home

mcp-elasticsearch

by AeaZer·9·Score 38

A fully-featured Elasticsearch MCP server with comprehensive search capabilities and multiple deployment options.

databasesearchdeveloper-tools
2
Forks
0
Open issues
10 mo ago
Last commit
2d ago
Indexed

Overview

This MCP server provides seamless integration with Elasticsearch clusters, offering a complete set of tools for cluster operations, index management, document operations, search capabilities, and bulk operations. It supports multiple protocols (stdio, HTTP, and deprecated SSE) and is compatible with Elasticsearch versions 7, 8, and 9. The server can be deployed via Docker, compiled from source, or integrated into desktop applications like Claude Desktop and Cursor with comprehensive configuration options.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:Enabling LLM assistants to query and interact with Elasticsearch data stores
you:Automating data management workflows through AI tool calling
you:Providing search capabilities to AI applications without requiring direct API access
you:Which Elasticsearch versions are supported?
you:What authentication methods are supported?

When to choose this

Choose this server when working with Elasticsearch clusters and need AI agents to perform data operations, search queries, and cluster management through MCP.

When NOT to choose this

Don't choose this if you're using a different search engine or need specialized features not supported by the Elasticsearch API.

Tools this server exposes

12 tools extracted from the README
  • es_cluster_info

    Get cluster information and version details

  • es_cluster_health

    Get cluster health status and metrics

  • es_index_create

    Create new indices with settings and mappings

  • es_index_delete

    Delete existing indices

  • es_index_exists

    Check if an index exists

  • es_index_list

    List all indices with metadata

  • es_document_index

    Index documents with optional ID

  • es_document_get

    Retrieve documents by ID

  • es_document_update

    Update existing documents

  • es_document_delete

    Delete documents by ID

  • es_search

    Execute search queries with filters, sorting, and field selection

  • es_bulk

    Execute multiple operations in a single request

Comparable tools

opensearch-mcpsolr-mcpelasticsearch-kibana-mcppgvector-mcp

Installation

Installation

Using Docker (Recommended)

docker run -d -p 8080:8080 \
  -e MCP_PROTOCOL=http \
  -e ES_ADDRESSES=http://your-elasticsearch:9200 \
  ghcr.io/aeazer/mcp-elasticsearch:latest

From Source

go install github.com/AeaZer/mcp-elasticsearch@latest

Claude Desktop Configuration

Add to ~/.config/claude/config.json:

{
  "mcpServers": {
    "elasticsearch": {
      "command": "mcp-elasticsearch",
      "env": {
        "ES_ADDRESSES": "http://localhost:9200",
        "ES_VERSION": "8"
      }
    }
  }
}

FAQ

Which Elasticsearch versions are supported?
This server is compatible with Elasticsearch versions 7, 8, and 9.
What authentication methods are supported?
Supports basic authentication (username/password), API keys, and Elastic Cloud authentication.

Compare mcp-elasticsearch with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.