Connect agents to Elasticsearch data via MCP
Top 75.6% on sourcepulse
This project provides an experimental Elasticsearch MCP server that allows Model Context Protocol (MCP) clients to interact with Elasticsearch indices via natural language. It targets users who want to query their Elasticsearch data using conversational AI, offering tools for listing indices, retrieving mappings, performing searches, and executing ES|QL queries.
How It Works
The server acts as a bridge, translating natural language requests from MCP clients into Elasticsearch queries. It supports various interaction protocols including stdio, SSE, and streamable-HTTP, with streamable-HTTP being the recommended and more modern approach. Authentication is handled via API keys or basic username/password credentials.
Quick Start & Requirements
docker.elastic.co/mcp/elasticsearch
).docker run -i --rm -e ES_URL -e ES_API_KEY docker.elastic.co/mcp/elasticsearch stdio
docker run --rm -e ES_URL -e ES_API_KEY -p 8080:8080 docker.elastic.co/mcp/elasticsearch http
ES_URL
, ES_API_KEY
(or ES_USERNAME
, ES_PASSWORD
), and optionally ES_SSL_SKIP_VERIFY
.Highlighted Details
Maintenance & Community
Licensing & Compatibility
Limitations & Caveats
This MCP server is explicitly marked as EXPERIMENTAL. Support for Elasticsearch versions prior to 8.x is not guaranteed. The ability to provide custom SSL certificates is planned for a future release.
4 days ago
Inactive