# Elasticsearch

This MCP server lets AI agents query Elasticsearch indices in natural language. It is deprecated and will receive critical security updates only.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: elastic
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/elastic/mcp-server-elasticsearch
- Updated: 2026-10-29
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/elastic-elasticsearch

## What it does

The server connects an AI agent to Elasticsearch through the Model Context Protocol. An agent can query indices and retrieve records from a natural-language request, without a custom API for each task. Choose stdio for a direct client connection or streamable-HTTP for web integrations and concurrent clients.

You need an Elasticsearch 8.x or 9.x cluster reachable from AWS, Docker, network access to the cluster, and valid credentials. Set `ES_URL` and authenticate with either `ES_API_KEY` or `ES_USERNAME` plus `ES_PASSWORD`. For stdio, start the container with `docker run -i --rm -e ES_URL -e ES_API_KEY docker.elastic.co/mcp/elasticsearch stdio`; HTTP mode uses `http` and port `8080`. The connection will fail if the cluster cannot be reached or the credentials are invalid.

Elastic has deprecated this server and plans to provide critical security updates only. Its suggested replacement is the MCP endpoint in Elastic Agent Builder, available in Elastic 9.2.0+ and Elasticsearch Serverless projects. That status matters when choosing a server for a new deployment.

## Requirements
- Needs: Docker

## Install

### Claude Code (native platform)

**Install**
- The MCP registry has no launch command for it: see the repository README

## When to use it
- query Elasticsearch indices with natural-language requests
- retrieve cluster records without creating a separate API for each task
- connect concurrent clients through streamable-HTTP
- check whether an agent can access Elasticsearch indices

## Example prompts
- Search my Elasticsearch indices for records related to …
- Analyze the data in my Elasticsearch cluster and return matching documents.
- Check whether you can retrieve records from the Elasticsearch indices.

## Similar
- [elasticsearch-best-practices](https://affpapa.org/en/nevibecode/skills/elasticsearch-best-practices.md) — skill · 1000 installs
- [elasticsearch-onboarding](https://affpapa.org/en/nevibecode/skills/elasticsearch-onboarding.md) — skill · 4900 installs
- [elasticsearch-esql](https://affpapa.org/en/nevibecode/skills/elasticsearch-esql.md) — skill · 5300 installs
- [elasticsearch-expert](https://affpapa.org/en/nevibecode/skills/elasticsearch-expert.md) — skill · 205 installs
- [elasticsearch-mcp-server](https://affpapa.org/en/nevibecode/mcp/elasticsearch-mcp-server.md) — MCP server · ★ 320 repo stars
- [alibabacloud-elasticsearch-instance-diagnose](https://affpapa.org/en/nevibecode/skills/alibabacloud-elasticsearch-instance-diagnose.md) — skill · 127 installs

## Other versions with the same name
- [Elasticsearch · tocharianou](https://affpapa.org/en/nevibecode/mcp/elasticsearch.md) — ★ 8 repo stars

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
