Provides a one-liner to run Elasticsearch in a Docker container for easy setup and deployment of the required backend.
Enables management of Elasticsearch clusters, allowing for creating indices, indexing documents, listing available indices, and executing search queries using Elasticsearch query DSL.
Elasticsearch
A Model Context Protocol server for Elasticsearch clusters. Enables LLMs to manage indices and execute queries.
IMPORTANT NOTE : this was built mainly by feeding examples to claude from the postgres mcp server.
Components
Tools
search
Execute search queries against indices
Input:
index(string): Target index namequery(object): Elasticsearch query DSL
Returns search hits
create_index
Create new Elasticsearch indices
Input:
index(string): Index namemappings(object, optional): Index mappings configurationsettings(object, optional): Index settings configuration
list_indices
List all available indices
No input required
Returns array of index information
index_document
Index a document
Input:
index(string): Target index nameid(string, optional): Document IDdocument(object): Document content
Returns indexing operation result
Resources
The server provides mapping information for each index:
Index Mappings (
elasticsearch://<host>/<index>/schema)JSON mapping information
Field names, types and configurations
Automatically discovered from metadata
Related MCP server: MongoDB MCP Server for LLMs
Usage with Claude Desktop
Add to the "mcpServers" section of your claude_desktop_config.json:
Docker one liner to run container :
Replace the URL with your Elasticsearch endpoint.
License
Licensed under MIT License. Free to use, modify, and distribute. See LICENSE file for details.