Elasticsearch
Connects agents to Elasticsearch data, enabling natural language interaction with indices.
Elasticsearch MCP Server
[!CAUTION] This MCP server is deprecated and will only receive critical security updates going forward. It has been superseded by Elastic Agent Builder's MCP endpoint, which is available in Elastic 9.2.0+ and Elasticsearch Serverless projects.
Connect to your Elasticsearch data directly from any MCP Client using the Model Context Protocol (MCP).
This server connects agents to your Elasticsearch data using the Model Context Protocol. It allows you to interact with your Elasticsearch indices through natural language conversations.
Available Tools
list_indices: List all available Elasticsearch indicesget_mappings: Get field mappings for a specific Elasticsearch indexsearch: Perform an Elasticsearch search with the provided query DSLesql: Perform an ES|QL queryget_shards: Get shard information for all or specific indices
Prerequisites
- An Elasticsearch instance
- Elasticsearch authentication credentials (API key or username/password)
- An MCP Client (e.g. Claude Desktop, Goose)
Supported Elasticsearch versions
This works with Elasticsearch versions 8.x and 9.x.
Installation & Setup
[!NOTE]
Versions 0.3.1 and earlier were installed via
npm. These versions are deprecated and no longer supported. The following instructions only apply to 0.4.0 and later.To view instructions for versions 0.3.1 and earlier, see the README for v0.3.1.
This MCP server is provided as a Docker image at docker.elastic.co/mcp/elasticsearch
that supports MCP's stdio, SSE and streamable-HTTP protocols.
Running this container without any argument will output a usage message:
docker run docker.elastic.co/mcp/elasticsearch
Usage: elasticsearch-mcp-server <COMMAND>
Commands:
stdio Start a stdio server
http Start a streamable-HTTP server with optional SSE support
help Print this message or the help of the given subcommand(s)
Options:
-h, --help Print help
-V, --version Print version
Using the stdio protocol
The MCP server needs environment variables to be set:
ES_URL: the URL of your Elasticsearch cluster- For authentication use either an API key or basic authentication:
- API key:
ES_API_KEY - Basic auth:
ES_USERNAMEandES_PASSWORD
- API key:
- Optionally,
ES_SSL_SKIP_VERIFYset totrueskips SSL/TLS certificate verification when connecting to Elasticsearch. The ability to provide a custom certificate will be added in a later version.
The MCP server is started in stdio mode with this command:
docker run -i --rm -e ES_URL -e ES_API_KEY docker.elastic.co/mcp/elasticsearch stdio
The configuration for Claude Desktop is as follows:
{
"mcpServers": {
"elasticsearch-mcp-server": {
"command": "docker",
"args": [
"run", "-i", "--rm",
"-e", "ES_URL", "-e", "ES_API_KEY",
"docker.elastic.co/mcp/elasticsearch",
"stdio"
],
"env": {
"ES_URL": "<elasticsearch-cluster-url>",
"ES_API_KEY": "<elasticsearch-API-key>"
}
}
}
}
Using the streamable-HTTP and SSE protocols
Note: streamable-HTTP is recommended, as SSE is deprecated.
The MCP server needs environment variables to be set:
ES_URL, the URL of your Elasticsearch cluster- For authentication use either an API key or basic authentication:
- API key:
ES_API_KEY - Basic auth:
ES_USERNAMEandES_PASSWORD
- API key:
- Optionally,
ES_SSL_SKIP_VERIFYset totrueskips SSL/TLS certificate verification when connecting to Elasticsearch. The ability to provide a custom certificate will be added in a later version.
The MCP server is started in http mode with this command:
docker run --rm -e ES_URL -e ES_API_KEY -p 8080:8080 docker.elastic.co/mcp/elasticsearch http
If for some reason your execution environment doesn't allow passing parameters to the container, they can be passed
using the CLI_ARGS environment variable: docker run --rm -e ES_URL -e ES_API_KEY -e CLI_ARGS=http -p 8080:8080...
The streamable-HTTP endpoint is at http:<host>:8080/mcp. There's also a health check at http:<host>:8080/ping
Configuration for Claude Desktop (free edition that only supports the stdio protocol).
-
Install
mcp-proxy(or an equivalent), that will bridge stdio to streamable-http. The executable will be installed in~/.local/bin:uv tool install mcp-proxy -
Add this configuration to Claude Desktop:
{ "mcpServers": { "elasticsearch-mcp-server": { "command": "/<home-directory>/.local/bin/mcp-proxy", "args": [ "--transport=streamablehttp", "--header", "Authorization", "ApiKey <elasticsearch-API-key>", "http://<mcp-server-host>:<mcp-server-port>/mcp" ] } } }
Related Servers
CData API Driver MCP Server
A read-only MCP server for querying live data from various APIs using the CData JDBC Driver for API Driver.
Database
Universal database MCP server supporting multiple database types including PostgreSQL, Redshift, CockroachDB, MySQL, RDS MySQL, Microsoft SQL Server, BigQuery, Oracle DB, and SQLite
Microsoft Access Database
Allows AI to interact with Microsoft Access databases, supporting data import and export via CSV files.
MySQL MCP Server
Provides direct access to MySQL databases, allowing AI agents to execute SQL queries and manage database content.
OpenGenes
Access the OpenGenes database for aging and longevity research, with automatic updates from Hugging Face Hub.
Grist
Integrate with the Grist API to manage relational spreadsheets and data. Requires a Grist API key.
Local Context Memory MCP
A production-ready persistent memory system for AI agents, offering searchable memory across sessions with semantic search and support for multiple database backends.
Mongo
A Model Context Protocol (MCP) server that enables LLMs to interact directly with MongoDB databases
CData SAP HANA XS Advanced Server
A read-only MCP server for SAP HANA XS Advanced, powered by the CData JDBC Driver.
Acumatica MCP Server by CData
A read-only MCP server for querying live Acumatica data using the CData JDBC Driver.